export const article = {
  author: 'Samuel Su',
  date: '2025-11-24',
  title: `Claude Opus 4.5 Now Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['Claude Opus 4.5', 'AI Models', 'Anthropic', 'Customer Support'],
  thumbnail,
  preview: `We're excited to announce Anthropic's Claude Opus 4.5 on Chat Data. The most advanced Opus model yet, delivering exceptional accuracy and improved efficiency for your customer support.

**Key improvements:**
- Industry-leading accuracy with 80%+ SWE-bench performance
- 48-76% better token efficiency for cost-effective operations
- Superior context understanding for complex conversations

Available now in your Chat Data model selector.`,
};


We're excited to announce the availability of Anthropic's Claude Opus 4.5 on Chat Data. This latest flagship model brings exceptional accuracy, superior reasoning capabilities, and improved efficiency to your customer support chatbots.

## What's New

- **Claude Opus 4.5**: Most advanced Opus model with breakthrough 80%+ SWE-bench accuracy

## Key Improvements for Customer Support

- **Higher Accuracy**: Industry-leading performance with significantly reduced hallucinations
- **Better Cost Efficiency**: 48-76% better token efficiency for high-volume conversations
- **Extended Autonomous Work**: Handles complex, multi-turn customer conversations effortlessly
- **Improved Context Understanding**: Superior conversation flow and information retention

Claude Opus 4.5 is now available in your Chat Data model selector, offering premium performance for businesses that need the highest quality AI responses.

Claude Opus 4.5 Now Available

export const article = {
  author: 'Samuel Su',
  date: '2025-11-19',
  title: `Gemini 3.0 Pro Now Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['Gemini 3.0 Pro', 'Google DeepMind', 'AI Models', 'Advanced Reasoning', 'Customer Support'],
  thumbnail,
  preview: `Google DeepMind's Gemini 3.0 Pro is now available on Chat Data, featuring state-of-the-art reasoning for complex problem-solving, enhanced customer intent understanding, and optimized performance at the same cost as previous Gemini models. We're currently using the Preview model and will automatically upgrade to the standard version when available.`,
};


We're excited to announce the availability of Google DeepMind's Gemini 3.0 Pro on Chat Data. This flagship model brings state-of-the-art reasoning capabilities and enhanced performance to your customer support chatbots.

## New Model

- **Gemini 3.0 Pro**: Google's most advanced model with exceptional reasoning capabilities and performance across complex tasks

## Key Improvements for Chatbots

- **Advanced Reasoning**: State-of-the-art performance for complex problem-solving and multi-step tasks
- **Enhanced Understanding**: Superior comprehension of customer intent across text and multimodal content
- **Improved Code & Logic**: Better handling of technical support questions and debugging scenarios
- **Optimized Performance**: Faster responses with dynamic thinking levels for different query complexities
- **Same Cost**: Credit cost remains the same as previous Gemini models

## Important Note

We are currently using the **Gemini 3.0 Pro Preview** model. When Google releases the standard Gemini 3.0 Pro model, we will automatically upgrade all chatbots to use the standard version with no action required on your part.

Gemini 3.0 Pro is now available in your Chat Data model selector.

Gemini 3.0 Pro Now Available

export const article = {
  author: 'Yongrui Su',
  date: '2025-11-18',
  title: `Launch: Real-Time PII De-Anonymization for Natural AI Conversations`,
  avatar: '/images/yongrui_su_profile.jpeg',
  hashtags: ['Privacy Protection', 'User Experience', 'PII Anonymization', 'Conversational AI'],
  thumbnail,
  preview: `We've completed the privacy loop with automatic PII de-anonymization! Your AI now delivers natural, readable responses while keeping customer data completely protected from LLM providers.

**Highlights**

🔒 **Full Privacy Protection** - Customer PII never reaches AI models

✨ **Natural User Experience** - Users see clean responses without ugly placeholder tokens

🤖 **Automatic Operation** - Works seamlessly when anonymization is enabled
`,
};


When we launched PII Anonymization, we gave you the power to protect your customers' sensitive data from AI models. But there was a catch: while the AI model never saw real emails, phone numbers, or names, your end users saw responses filled with ugly placeholder tokens like PERSON_7299dd, EMAIL_ADDRESS_217195, and PHONE_NUMBER_862c7c.

Today, we're completing the privacy loop with automatic PII de-anonymization - giving you the best of both worlds with full privacy protection AND natural, readable responses.

---

## The Problem We Solved

When PII Anonymization was enabled, users would see responses filled with ugly placeholder tokens instead of natural language.

**User Query:**
```plaintext
Summary below: Our team members are: Alice, phone 555-1111; Bob, phone 555-2222;
and Carol, phone 555-3333. Their email addresses are: alice@company.com,
bob@company.com, and carol@company.com. Please contact headquarters at phone
number 555-4444.
```

**What Users Saw Before (With Placeholders):**
```plaintext
Here's a cleaned-up, natural-language version of your summary with placeholders
preserved:

Our [PERSON_7299dd] are:

[PERSON_64489c], phone [PHONE_NUMBER_862c7c]
[PERSON_2fc1c0], phone [PHONE_NUMBER_793eec]
[PERSON_150c16], phone [PHONE_NUMBER_517ce1]

Their email addresses are:
[EMAIL_ADDRESS_2353b2]
[EMAIL_ADDRESS_217195]
[EMAIL_ADDRESS_f95f10]

Please contact headquarters at phone number [PHONE_NUMBER_9a5359].
```

The privacy worked perfectly - the AI never saw the real data. But the user experience was terrible.

---

## The Solution

**What Users See Now (Natural Language):**
```plaintext
Here's a cleaned-up, natural-language version of your summary:

Our team members are:

Alice, phone 555-1111
Bob, phone 555-2222
Carol, phone 555-3333

Their email addresses are:
alice@company.com
bob@company.com
carol@company.com

Please contact headquarters at phone number 555-4444.
```

Same privacy protection. Natural user experience. Automatic.

---

## How It Works

The magic happens automatically:

🔒 **What the AI Sees:** PERSON_64489c, EMAIL_ADDRESS_2353b2, PHONE_NUMBER_862c7c

✨ **What Your Users See:** Alice, alice@company.com, 555-1111

Your customer data never reaches the AI provider, but your users always see natural, readable responses.

---

## Why This Matters

🔒 **Full Privacy** - AI never sees real names, emails, or phone numbers

✨ **Natural Conversations** - No more ugly PERSON_7299dd tokens breaking the user experience

🤖 **Zero Setup** - Already works if you have PII anonymization enabled

🚀 **No Delays** - Happens instantly during streaming

Whether you're in e-commerce handling order details, healthcare protecting patient information, financial services managing sensitive accounts, or customer support - your users now get clean, readable responses while their data stays completely protected.

---

## Getting Started

De-anonymization works automatically with nothing to configure!

If you already have Anonymize PIIs for LLM enabled in Settings then Privacy, de-anonymization is now active. Your users will see natural responses instead of placeholder tokens while your customer data stays fully protected from AI models.

If you haven't enabled PII anonymization yet, head to Settings then Privacy and toggle on Anonymize PIIs for LLM to start protecting customer data with automatic de-anonymization built in.

Launch: Real-Time PII De-Anonymization for Natural AI Conversations

export const article = {
  author: 'Yongrui Su',
  date: '2025-11-16',
  title: `AI Search Bar & Enhanced Widget Experience`,
  avatar: '/images/yongrui_su_profile.jpeg',
  hashtags: ['Widget', 'UX', 'Page Context', 'AI Search'],
  thumbnail: searchBarWidget,
  preview: `
Transform your website's AI experience with the new AI Search Bar widget and powerful contextual awareness features that make customer interactions more intuitive and intelligent.

**Highlights**

🔍 **AI Search Bar Widget** - New sleek search bar display style alongside the traditional chat bubble for a seamless on-page experience

⚡ **Direct Interaction** - Conversation starters now appear directly on your website—no need to open the widget first

📝 **Ask AI About Selection** - Customers can select any text on your page and instantly ask AI about it with one click

🧠 **Page Awareness by Default** - Chatbot automatically understands page content, navigation, and user context for personalized responses

🔒 **Privacy Protected** - Built-in PII anonymization keeps personal information safe while maintaining conversation context

📱 **Full-Screen Mode** - Users can expand the widget to full-screen size for a more immersive chat experience on desktop
`,
};


We're excited to launch major improvements to the Chat Data widget experience—making it easier for your customers to interact with your AI chatbot and get personalized, context-aware responses instantly.


---

## AI Search Bar Widget Style

You now have **two display styles** to choose from when embedding your chatbot on your website:

🔵 **Chat Bubble** - The familiar floating chat bubble that appears in the corner of your page, perfect for persistent support access.

🔍 **AI Search Bar** - A sleek, modern search bar that blends naturally into your page layout, ideal for knowledge bases, documentation sites, and content-heavy pages where users expect to search for information.

Both styles provide the same powerful AI capabilities—choose the one that best matches your website's design and user expectations. You can configure this in **Settings > Chat Interface > Display Style**.

---

## Direct Conversation Starters

Say goodbye to the extra click! Conversation starters (suggestion questions) now appear **directly on your website** instead of only inside the chatbot interface.


⚡ **Instant Engagement** - Customers can click a suggested question right from your page to start a conversation without opening the widget first.

🎯 **Lower Friction** - Reduce the barrier to engagement by showing relevant questions upfront based on the current page context.

💡 **Better Discovery** - Visitors immediately see what your chatbot can help with, increasing interaction rates and improving the customer experience.

Previously, users had to open the chatbot widget and then click on conversation starters inside the chat interface. Now they can engage instantly with one click.

---

## Enhanced Suggestion Messages Control

We've separated the controls for suggestion message generation and visibility, giving you more flexibility to optimize both AI costs and user experience across different devices.

**Three Independent Controls:**

🤖 **Dynamic Suggestion Generation** - Control how many AI-generated suggestion questions to create based on conversation context (1-5 suggestions). This determines how many questions the AI will generate, which impacts your AI usage costs.

💻 **Visible Suggestions (Desktop)** - Control how many suggestion messages display when the widget is closed on desktop screens. This is purely a display setting and doesn't affect AI generation.

📱 **Visible Suggestions (Mobile)** - New mobile-specific setting for narrow screens. Choose a smaller number of suggestions to display on mobile devices where screen space is limited, while still generating the full set in the background.



**Why This Matters:**

- **Cost Optimization** - Generate fewer suggestions to reduce AI costs without changing what users see
- **Mobile Experience** - Show fewer suggestions on mobile to avoid cluttering small screens
- **Flexibility** - Configure generation and visibility independently based on your needs

**Example Use Case:** You might generate 5 dynamic suggestions for better variety, but only show 3 on desktop and 2 on mobile to keep the interface clean.

Configure these settings in **Settings > Chat Interface > Suggestion Messages**.

---

## Ask AI About Selected Text

Give your customers the power to ask about **any content on your page** with the new "Ask AI" feature.


📝 **Text Selection Magic** - When a user selects any text on your website, an "Ask AI" button appears automatically above the selection.

💬 **Instant Context** - Clicking the button opens the chatbot with the selected text pre-populated, ready for questions like "Explain this," "What does this mean?" or "Tell me more about this."

🎓 **Perfect for Education & Documentation** - Ideal for technical docs, educational content, product descriptions, or any site where users might need clarification on specific passages.

This feature works seamlessly with both the chat bubble and AI search bar widget styles.

---

## Page Awareness by Default

Your chatbot is now **automatically aware of the page context** when integrated through the widget—no configuration needed.

🧠 **Smart Context Understanding** - The chatbot receives key information about the current page including:
- Navigation links and site structure
- Important factual information visible on the page
- User information (if available)
- Current page URL and context

🎯 **Personalized Responses** - By combining your knowledge base with real-time page content, the chatbot delivers more accurate, contextually relevant answers tailored to what the customer is currently viewing.

💡 **Better Customer Experience** - Instead of relying solely on static knowledge base content, your chatbot understands where the customer is on your site and what they're looking at.

### Privacy Protection

Concerned about sensitive information from page content reaching AI models? We've got you covered:

🔒 **Automatic PII Anonymization** - Enable "Anonymize PIIs for LLM" in **Settings > Privacy** to automatically mask personal information (emails, phone numbers, credit cards, etc.) from page content before it's sent to AI models.

⚙️ **Full Control** - Want to disable page context entirely? Simply turn off the "Enable Page Context" option in **Settings > Chat Interface > Other Configuration** to stop tracking page content and URLs.

**Note:** Page awareness is enabled by default for all chatbots using the widget integration. You don't need to do anything to turn it on—it just works.

---

## Full-Screen Widget Mode

Give your customers more space to interact with your AI chatbot with the new full-screen expansion option.


📱 **Desktop Optimization** - Users can expand the chatbot widget to fill their entire screen for a more immersive chat experience, perfect for complex conversations or when reviewing detailed responses.

🔄 **Easy Toggle** - One click expands to full-screen, another click returns to the original widget size—simple and intuitive.

💼 **Professional Experience** - Great for enterprise users, support conversations, or when customers need to reference extensive documentation or product details in the chat.

This feature is available for both chat bubble and AI search bar widget styles on desktop devices.

---

## Getting Started

All these features are **available now** for your Chat Data chatbots:

1. **Choose Your Widget Style** - Go to **Settings > Chat Interface > Display Style** to select between chat bubble and AI search bar
2. **Configure Page Context** - Visit **Settings > Chat Interface > Other Configuration** to manage page awareness settings
3. **Enable Privacy Protection** - Head to **Settings > Privacy** to turn on PII anonymization for page content
4. **Test the Experience** - Use the embedding simulator to see how conversation starters, text selection, and full-screen mode work together

These enhancements work seamlessly across all your existing chatbot configurations and integrations. No migration or code changes required—just update your settings and start delivering a better customer experience today.

AI Search Bar & Enhanced Widget Experience

export const article = {
  author: 'Samuel Su',
  date: '2025-11-13',
  title: `GPT-5.1 Now Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['GPT-5.1', 'OpenAI', 'AI Models', 'Customer Support'],
  thumbnail,
  preview: `We're excited to announce the availability of OpenAI's GPT-5.1 on Chat Data. This flagship model brings state-of-the-art performance and significantly reduced hallucinations to your customer support chatbots.

## New Model

- **GPT-5.1**: OpenAI's flagship model with exceptional accuracy and fastest response times for straightforward queries

## Key Improvements for Chatbots

- **Superior Accuracy**: State-of-the-art performance across all domains with significantly reduced hallucinations
- **Faster Responses**: Up to 2x faster on straightforward customer queries for real-time support
- **Better Understanding**: More accurate interpretation of customer intent and questions
- **Enhanced Reliability**: Fewer errors and more consistent responses for automated support

GPT-5.1 is now available in your Chat Data model selector.`,
};


We're excited to announce the availability of OpenAI's GPT-5.1 on Chat Data. This flagship model brings state-of-the-art performance and significantly reduced hallucinations to your customer support chatbots.

## New Model

- **GPT-5.1**: OpenAI's flagship model with exceptional accuracy and fastest response times for straightforward queries

## Key Improvements for Chatbots

- **Superior Accuracy**: State-of-the-art performance across all domains with significantly reduced hallucinations
- **Faster Responses**: Up to 2x faster on straightforward customer queries for real-time support
- **Better Understanding**: More accurate interpretation of customer intent and questions
- **Enhanced Reliability**: Fewer errors and more consistent responses for automated support

GPT-5.1 is now available in your Chat Data model selector.

GPT-5.1 Now Available

export const article = {
  author: 'Yongrui Su',
  date: '2025-10-29',
  title: `Protect Sensitive Data with PII Anonymization`,
  avatar: '/images/yongrui_su_profile.jpeg',
  hashtags: ['Data Masking', 'PII Protection', 'AI Data Privacy', 'GDPR Compliance'],
  thumbnail,
  preview: `
Automatically protect your customers' personal information before it reaches your AI models, while keeping conversation context intact for excellent support.

**Highlights**

🔒 **Flexible PII Protection** - Choose which personal data to anonymize per workspace or integration—from emails and phone numbers to credit cards and national IDs

✅ **Intelligent Pre-Processing** - Automatically mask sensitive data before it reaches AI models or gets stored, with no workflow changes needed

🌍 **Privacy by Default** - Meet GDPR and data minimization requirements while maintaining full conversation context for your team
`,
};


We're excited to launch **PII Anonymization**—automatically protect your customers' personal information before it reaches your AI models, while keeping conversation context intact so your team can deliver excellent support.

---

## What is PII Anonymization?

PII Anonymization is your **automatic privacy shield** that sits between your customers and your AI systems. Think of it as a smart filter that identifies and masks personal information—like email addresses, phone numbers, credit cards, and national IDs—before that data reaches your AI models or gets stored in Chat Data.

🔒 **Works Automatically** - Once enabled, every customer message is scanned and sensitive data is replaced with consistent placeholders like EMAIL_1 or PHONE_1.

💬 **Preserves Context** - Your AI and support team still see the full conversation flow and can reference "the email address" or "that phone number" without seeing the actual values.

🎯 **Granular Control** - Choose exactly which types of personal data to protect, and apply different rules per workspace or integration.

---

## Why This Matters for Your Business

When customers share personal details with your chatbot, you want to provide great service while keeping their information secure. PII Anonymization gives you both:

**For E-commerce & Retail**
Customers naturally share order numbers, shipping addresses, and payment details. Anonymization lets your AI help with order tracking and support without exposing sensitive transaction data to third-party models.

**For Healthcare & Wellness**
Patient inquiries often include medical IDs, insurance numbers, and personal health details. Keep your AI assistance HIPAA-friendly by masking identifiers before they reach your LLM provider.

**For Financial Services**
Banking and fintech conversations involve account numbers, tax IDs, and transaction details. Anonymization protects customer data while your AI provides account support and answers questions.

**For Everyone**
🛡️ **Customer Trust** - Show customers you take their privacy seriously by protecting their data by default.
📊 **Safe AI Training** - Use conversation data to improve your chatbot without worrying about sensitive information leaking into training sets.
✅ **Simple Compliance** - Meet GDPR, CCPA, and SOC 2 data minimization requirements without building custom middleware or rewriting your workflows.

---

## What You Can Protect

PII Anonymization gives you fine-grained control over exactly which types of personal information get masked. Here's what you can configure:

### Built-in Protection Categories

Toggle anonymization for any of these common personal identifiers:

- 👤 **Name - Person Identification** - Full names and personal identifiers
- 📧 **Email Address** - Email addresses in any format
- 📱 **Phone Number** - Phone numbers with international format support
- 💳 **Credit Card Number** - Payment card numbers and related tokens
- 🌐 **IP Address** - IPv4 and IPv6 addresses
- 📍 **Location - Address Information** - Physical addresses and location details
- 🆔 **Tax Identification Number** - Social security numbers, VAT IDs, and tax identifiers
- 🏥 **Medical Information** - Medical license numbers and health identifiers
- 🏦 **Banking Details** - Account numbers, IBAN codes, and routing numbers
- 🚗 **Government IDs** - Passport numbers, driver's licenses, and national ID cards

### Smart Placeholders

When data is anonymized, it's replaced with **consistent, descriptive placeholders** like EMAIL_1, PHONE_2, or CREDIT_CARD_1. This means:
- Your AI can still reference "the email address" in conversation naturally
- Your support team sees the full conversation flow and context
- Automations and workflows continue working without modification
- The same email address always gets the same placeholder ID within a conversation

---

## How It Works

PII Anonymization operates automatically in the background with zero workflow changes required. When a customer shares sensitive information, the system instantly detects and replaces it with consistent placeholders like EMAIL_1, PHONE_1, or CREDIT_CARD_1 before the data reaches your AI models or gets stored.

Your AI and team still see full conversation context and can naturally reference "the email address" or "that phone number" without ever seeing the actual values. This means you can analyze patterns, train models, and deliver excellent support while keeping customer data private by default.

---

## Getting Started

Ready to protect your customer data? Head to **Settings > Privacy** in your Chat Data workspace to enable protection categories and start anonymizing sensitive information automatically.

Protect Sensitive Data with PII Anonymization

export const article = {
  author: 'Yongrui Su',
  date: '2025-10-16',
  title: `Launch: Build Multi-Step AI Agent Workflows with Auto Prompt`,
  avatar: '/images/yongrui_su_profile.jpeg',
  hashtags: ['Workflow', 'Automation', 'AI', 'AI Agents'],
  thumbnail: workflowBuilderExample,
  preview: `
Transform your chatbot into an intelligent AI agent with **Workflows**—multi-step conversation paths for lead qualification, onboarding, appointment booking, and complex customer journeys.

**Highlights**

🎯 **Workflows as AI Actions** - Trigger complex, multi-step processes with isolated session management

🤖 **AI-Powered Generation** - Build workflows in natural language with Auto Prompt, or use manual drag-and-drop

🧪 **Visual Testing & Debugging** - Real-time node transitions with full debug info and AI-powered test simulations

🌐 **Multi-Platform Ready** - Deploy across website widgets and third-party integrations (WhatsApp, Messenger, Instagram, Telegram, Slack, Discord)

📦 **Easy Management** - Centralized variables, import/export workflows, and collaborate with your team
`,
};


We're excited to launch the **Workflow Builder**—a powerful new way to create sophisticated, multi-step chatbot experiences that go beyond simple conversations.


---

## What Are Workflows?

Workflows are **specific AI actions** that guide your chatbot through complex, multi-step processes. Think of them as automated conversation paths for lead qualification, customer onboarding, appointment booking, or any process that requires multiple steps and decision points.

🎯 **Triggered Like AI Actions** - Each workflow operates as a dedicated AI action that can be triggered just like your other chatbot actions.

🔄 **Isolated Sessions** - When a workflow starts, your chatbot enters a focused session following your defined logic step by step. Once complete, it returns to normal conversation and can trigger another workflow if needed.

🎭 **Flexible AI Behavior** - AI Conversation nodes within workflows can use completely different base prompts tailored to specific tasks, letting you optimize responses for each step.

⚡ **Clean Execution** - Only one workflow runs per conversation at a time, preventing conflicts and ensuring predictable paths.

---

## How to Build Workflows

Create workflows in two ways—whichever fits your needs:

### AI-Powered Generation (Recommended)

🤖 **Two-Phase Process** - Describe your goal in natural language, review the generated blueprint, give feedback, and regenerate until it's right. Works for both new workflows and updating existing ones.

✅ **Instant Build** - Once approved, AI builds the complete workflow with all nodes, variables, and connections.

🔄 **Easy Updates** - Use Auto Prompt to modify existing workflows too. Simply describe what you want to change, and AI will update your workflow to meet your new business goals.

🎯 **Smart Configuration** - AI automatically ensures proper data capture, branching logic, and integrations are configured correctly.

📊 **Safe Review** - Every AI-generated change is marked as unsaved so you can review before publishing.

💡 **Best Practice**: After AI generates your workflow, audit variable types—some boolean flags may be created as strings and should be corrected to ensure reliable condition checks (e.g., true/false instead of 'yes'/'true').

### Manual Drag-and-Drop

🎨 **Visual Canvas** - Drag-and-drop pre-built blocks for messaging, UI elements, data capture, conditional logic, automation, code execution, and variable management.

🎛️ **Node Editors** - Configure each step in the right panel with easy access to email content, API payloads, form fields, validation rules, and wait timers.

---

## Testing Your Workflows

Before going live, thoroughly test your workflows with built-in tools:

🧪 **Visual Testing Panel** - Watch real-time node transitions with full debug information showing exactly why the workflow moved from one step to another, making validation and troubleshooting effortless.

⚙️ **Test Scenarios** - Configure visitor presets, seed conversations with scripted openings, and let the simulator detect loops or stalled edges.

💾 **Test Set Management** - Save test scenarios and run AI-powered automatic simulations to verify your workflow behaves correctly across different user paths.

💬 **Live Debug Info** - Conversation transcripts, transition breadcrumbs, and variable snapshots update in real-time so you can verify your logic.

---

## Where Workflows Work

Deploy your workflows across all your customer touchpoints:

🌐 **Multi-Platform Support** - Workflows work seamlessly across website widgets and third-party integrations (WhatsApp, Messenger, Instagram, Telegram, Slack, Discord).

🎴 **Smart Adaptation** - Rich UI elements like carousel cards adapt intelligently to each platform. When a platform can't render interactive components, we automatically send the content as files.

🔌 **API Coming Soon** - API integration compatibility is in development for our next release.

---

## Managing Your Workflows

Keep your workflows organized and shareable:

🔐 **Centralized Variables** - Manage all your workflow variables in one place with easy search, rename, and organization capabilities.

📦 **Import/Export** - Share workflows across environments, collaborate with team members, or create backup copies with secure import and export functionality.

---

## What's Next

We're already working on the next wave of workflow enhancements:

🔌 **API Compatibility** - Enable workflows to work with API integrations

🌍 **Static Message Internationalization** - Automatically adapt static messages to match your visitors' browser language

📚 **More Templates** - Ready-to-use workflow templates you can customize for common use cases

🎨 **Additional UI Elements** - New interactive components based on your feedback to create richer user experiences

---

 Check out our [Workflow Builder documentation](https://cookbook.chat-data.com/docs/workflow) for detailed guides.

Launch: Build Multi-Step AI Agent Workflows with Auto Prompt

export const article = {
  author: 'Samuel Su',
  date: '2025-10-07',
  title: `New API Endpoint: Attach Lead & Enhanced Customer Filtering`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['API', 'Lead-Management', 'Filtering'],
  thumbnail,
  preview: `We've added a new **/attach-lead** endpoint and enhanced the /get-customers endpoint with filtering capabilities.

**What's New:**
- New POST **/attach-lead** endpoint to programmatically attach or update leads to conversations
- **/get-customers** now supports filtering by leadId, email, phone, name, psid, ig_username, and username
- All customer records now include leadId field for consistent reference
`,
};


We've released two API enhancements to improve lead management and customer data integration.

---

## New Endpoint: POST /attach-lead

Attach or update lead information for a specific conversation.

**Request Example:**

```bash
POST /api/v2/attach-lead
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "conversationId": "conv_123456",
  "chatbotId": "chatbot_789",
  "email": "customer@example.com",
  "phone": "+1234567890",
  "name": "John Doe"
}
```

**Response:**

```json
{
  "status": "success",
  "lead": {
    "leadId": "550e8400-e29b-41d4-a716-446655440000",
    "name": "John Doe",
    "email": "customer@example.com",
    "phone": "+1234567890",
    "source": "api"
  }
}
```

**Common Use Cases:**

- Sync customer data from your CRM (Salesforce, HubSpot, etc.) to Chat Data conversations
- Update lead information after purchases, form submissions, or user actions
- Link conversations across channels (web, WhatsApp, Messenger) to the same customer record

**Key Features:**

- Searches for existing leads using all provided fields (best-effort matching)
- Creates new leads automatically if no match is found
- UUID cannot be changed once a lead exists
- Supports fields: email, phone, name, psid, ig_username, username, uuid

---

## Enhanced: GET /get-customers

The /get-customers endpoint now supports filtering and includes leadId in responses.

**New Query Parameters:**

- leadId - Filter by lead identifier
- email - Filter by email address
- phone - Filter by phone number
- name - Filter by customer name
- psid - Filter by Page Scoped User ID
- ig_username - Filter by Instagram username
- username - Filter by username

**Example Request:**

```bash
GET /api/v2/get-customers/chatbot_789?email=customer@example.com
Authorization: Bearer YOUR_API_KEY
```

**Example Response:**

```json
{
  "status": "success",
  "customers": [
    {
      "leadId": "550e8400-e29b-41d4-a716-446655440000",
      "name": "John Doe",
      "email": "customer@example.com",
      "phone": "+1234567890",
      "source": "widget",
      "createdAt": 1696118400000
    }
  ],
  "total": 1
}
```

**Common Use Cases:**

- Look up specific customers by email or phone number
- Filter customers by source and other attributes for reporting
- Use leadId to cross-reference customers across different API endpoints

---

## Getting Started

**Step 1:** Get your API key from Account Settings → API Keys or Chatbot Settings → API Keys

**Step 2:** Try the endpoints

```bash
# Attach a lead to a conversation
curl -X POST https://api.chat-data.com/api/v2/attach-lead \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "conversationId": "your_conversation_id",
    "chatbotId": "your_chatbot_id",
    "email": "customer@example.com",
    "name": "John Doe"
  }'

# Filter customers by email
curl -X GET "https://api.chat-data.com/api/v2/get-customers/your_chatbot_id?email=customer@example.com" \
  -H "Authorization: Bearer YOUR_API_KEY"
```

---

## Documentation

For complete API specifications, request/response schemas, and error handling details, see:

- [API Reference - /attach-lead](/api-reference#tag/Conversation-Operations/operation/AttachLead)
- [API Reference - /get-customers](/api-reference#tag/Chatbot-Analytics/operation/GetCustomers)

Available now for all plans with API access. See [PR #1281](https://github.com/chat-data/chat-data/pull/1281) for technical implementation details.

New API Endpoint: Attach Lead & Enhanced Customer Filtering

export const article = {
  author: 'Samuel Su',
  date: '2025-09-30',
  title: `Claude 4.5 Sonnet Now Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['Claude 4.5 Sonnet', 'AI Models', 'Anthropic', 'Technical Support', 'Finance', 'Cybersecurity'],
  thumbnail,
  preview: `We're thrilled to announce Claude 4.5 Sonnet on Chat Data. Anthropic's most advanced Sonnet model brings specialized domain expertise for technical, financial, and security-focused chatbots.

**Enhanced Domain Knowledge:**
- **Coding & Technical Support**: Developer documentation, troubleshooting, and technical guidance
- **Finance & Banking**: Complex financial inquiries and investment support
- **Cybersecurity**: Security advisory, compliance information, and best practices

Perfect for chatbots serving developers, fintech, cybersecurity, and complex technical support. Available now at 4 credits per message.`,
};


We're thrilled to announce the availability of Anthropic's Claude 4.5 Sonnet on Chat Data. This model brings specialized domain expertise and enhanced accuracy to your chatbots, making it ideal for technical, financial, and security-focused customer support.

## Enhanced Domain Expertise

Claude 4.5 Sonnet excels in specialized domains with deep knowledge in:

### Coding & Technical Support
- **Developer Documentation**: Accurately explain complex APIs, SDKs, and technical concepts
- **Code Troubleshooting**: Help customers debug issues and understand error messages
- **Technical Product Support**: Provide detailed technical guidance and best practices

### Finance & Banking
- **Financial Services Support**: Handle complex financial inquiries with accuracy
- **Investment Queries**: Provide informed responses about financial products and markets
- **Banking Assistance**: Support customers with account-related technical questions

### Cybersecurity
- **Security Advisory**: Answer security-related questions with expertise
- **Compliance Information**: Help customers understand security compliance requirements
- **Threat Awareness**: Provide informed guidance on security best practices

## Key Improvements

- **More Accurate Domain Responses**: Highest precision for specialized technical and financial queries
- **Better Complex Query Handling**: Superior performance on multi-step customer questions
- **Enhanced Problem Solving**: Deeper reasoning for detailed troubleshooting scenarios
- **Longer Conversation Context**: Maintains accuracy and detail across extended support sessions

## Ideal For

Claude 4.5 Sonnet is perfect for chatbots serving:
- Developer communities and technical documentation
- Financial services and fintech companies
- Cybersecurity products and services
- Complex technical product support

Claude 4.5 Sonnet is now available in your Chat Data model selector at 4 credits per message.

Claude 4.5 Sonnet Now Available

export const article = {
  author: 'Samuel Su',
  date: '2025-08-29',
  title: `OpenAI GPT-Realtime Now Available with 25% Lower Pricing`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['GPT-Realtime', 'Voice AI', 'OpenAI', 'Price Reduction'],
  thumbnail,
  preview: `OpenAI's production-ready GPT-Realtime model is now available on Chat Data with 25% credit cost reduction, 82.8% accuracy (26% improvement), and new natural-sounding voices. All agents using gpt-4o-realtime-preview have been automatically upgraded - no action required.`,
};


We're thrilled to announce the integration of OpenAI's production-ready GPT-Realtime model into Chat Data! This advanced voice AI model delivers superior performance, more natural conversations, and comes with a 25% price reduction.

## What's New

OpenAI's GPT-Realtime represents a significant upgrade from the preview version with enhanced accuracy, stability, and voice quality. The model achieves **82.8% accuracy** on benchmarks compared to 65.6% for the previous version.

## Key Improvements

- **More Natural Voices**: Two new voices - Cedar and Marin - deliver more expressive and natural-sounding speech
- **Better Accuracy**: 26% improvement in benchmark performance for more reliable responses  
- **Enhanced Stability**: Production-ready reliability with better instruction following
- **Multilingual Support**: Improved handling of multiple languages and accents

## 25% Price Reduction

We're passing on the savings! GPT-Realtime is 25% cheaper than the previous model:
- Text input: 0.75 credits per 1k tokens (was 1 credit)
- Text output: 3 credits per 1k tokens (was 4 credits)
- Audio input: 6 credits per 1k tokens (was 8 credits)
- Audio output: 12 credits per 1k tokens (was 16 credits)

## Automatic Migration

**No action required!** All AI agents previously using gpt-4o-realtime-preview have been automatically upgraded to GPT-Realtime. Agents using gpt-4o-mini-realtime-preview will remain unchanged as there's no mini version available yet.

OpenAI GPT-Realtime Now Available with 25% Lower Pricing

export const article = {
  author: 'Samuel Su',
  date: '2025-08-15',
  title: `Telegram Integration Is Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['telegram', 'integration', 'livechat', 'ai', 'customerservice'],
  thumbnail,
  preview: `
We're launching Telegram integration to help you connect with over 700 million active users worldwide through your AI chatbot.

## Key Features:

- **Global Reach:** Tap into Telegram's massive international user base
- **Instant Setup:** Create your bot in minutes with BotFather
- **Rich Media Support:** Handle images, documents, and audio seamlessly
- **Live Chat Handover:** Seamless transition from AI to human agents
- **Smart Response Options:** Choose between text, markdown, or audio formats

Get started by connecting your Telegram bot through the Integrations tab on your Dashboard.
`,
};


We're excited to launch Telegram integration, enabling your chatbot to reach Telegram's 700+ million users worldwide. This powerful integration combines AI automation with human support capabilities, perfect for global customer engagement.

## Key Updates:

- **Simple Bot Creation Process:**  
  - Create your bot instantly through Telegram's BotFather
  - Automatic webhook configuration for reliable message delivery
  - QR code generation for easy testing and sharing
  - No complex setup or coding required

- **Rich Media Capabilities:**  
  - Process and respond to images, documents, PDFs, and audio files
  - Support for voice messages with automatic transcription
  - Handle file uploads seamlessly within Telegram's generous limits
  - Automatic audio format conversion for optimal compatibility

- **Advanced Response Customization:**  
  - Multiple response formats: plain text, markdown formatting, or audio messages
  - Configurable response delays for natural conversation pacing
  - Follow-up message support to maintain customer engagement
  - Smart pause feature (up to 1 week) for initial setup and testing

- **Live Chat Integration:**  
  - Instant handover from AI to human agents when needed
  - Real-time conversation management through the Live Chat dashboard
  - Email notifications for messages received while offline
  - Full conversation history and context preservation

## Get Started:
- **New Users:** Navigate to Dashboard > [Chatbot] > Integrations and select the Telegram integration card
- **Setup Process:** Follow the simple BotFather instructions to create your bot and paste the token
- **Testing:** Use the provided QR code or direct link to test your bot instantly

Check the [Telegram Integration](https://cookbook.chat-data.com/docs/telegram-integration) page for detailed setup instructions.

Telegram Integration Is Available

export const article = {
  author: 'Samuel Su',
  date: '2025-08-11',
  title: `Chatbot-Specific API Keys Launch`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['API', 'SSO', 'Reseller', 'White-Label', 'Granular Control'],
  thumbnail,
  preview: `Introducing chatbot-specific API keys for granular access control—perfect for sharing API access without exposing your entire account.

### 🔑 Key Benefits

- **Granular Control**: Share API keys with clients or partners that only access specific chatbots, not your entire account
- **SSO Integration**: Perfect complement to SSO login—provide users with API access limited to their assigned chatbots
- **White-Label Ready**: Ideal for resellers who need to give clients API access to their chatbot without exposing other client chatbots
- **Multiple Keys**: Create up to 10 unique API keys per chatbot for different integrations

### 🎯 Perfect For

- **Resellers & Agencies**: Safely provide API access to individual client chatbots
- **Enterprise Teams**: Grant department-specific access without account-wide exposure
- **SSO Users**: Combine with SSO login to create fully isolated client environments
- **White-Label Solutions**: Maintain complete separation between different clients

### ⚡ Quick Start

1. Navigate to your chatbot's **Settings**
2. Click **API Keys** in the sidebar
3. Click **Create New Key**
4. Save the key securely (won't be shown again)

### ✅ Backward Compatible

Your existing user-level API keys continue working without any changes. Choose between account-wide or chatbot-specific keys based on your needs.

Available now for Entry, Standard, and Professional plans.`,
};


Introducing chatbot-specific API keys for granular access control—perfect for sharing API access without exposing your entire account.

### 🔑 Key Benefits

- **Granular Control**: Share API keys with clients or partners that only access specific chatbots, not your entire account
- **SSO Integration**: Perfect complement to SSO login—provide users with API access limited to their assigned chatbots  
- **White-Label Ready**: Ideal for resellers who need to give clients API access to their chatbot without exposing other client chatbots
- **Multiple Keys**: Create up to 10 unique API keys per chatbot for different integrations

### 🎯 Perfect For

- **Resellers & Agencies**: Safely provide API access to individual client chatbots
- **Enterprise Teams**: Grant department-specific access without account-wide exposure
- **SSO Users**: Combine with SSO login to create fully isolated client environments
- **White-Label Solutions**: Maintain complete separation between different clients

### 💡 Why This Matters

When using SSO login to provide clients access to their chatbots, you previously had to share user-level API keys that exposed all chatbots in your account. Now, chatbot-specific API keys solve this by:

1. **Isolating API Access**: Each client gets API keys that only work with their assigned chatbot
2. **Enhancing Security**: No risk of clients accidentally accessing other clients' data
3. **Simplifying Management**: Create, rename, and revoke keys independently for each chatbot

### ⚡ Getting Started

1. Navigate to your chatbot's **Settings** panel
2. Click **API Keys** in the sidebar (look for the "New" badge)
3. Click **Create New Key** 
4. Optionally name your key for easy identification
5. Save the generated key securely—it won't be shown again

### 🔧 Key Management Features

- **Custom Naming**: Organize keys with descriptive names
- **Usage Tracking**: See when each key was last used
- **Quick Actions**: Rename or revoke keys instantly
- **10 Keys per Chatbot**: Create multiple keys for different integrations

### ✅ Backward Compatibility

Your existing user-level API keys continue working without any changes. You can now choose:
- **User-Level Keys**: For account-wide access (existing behavior)
- **Chatbot-Specific Keys**: For granular, isolated access (new feature)

### 📚 Documentation

For API integration details, visit our [API Reference](https://www.chat-data.com/api-reference).

Available now for Entry, Standard, and Professional plans.

Chatbot-Specific API Keys Launch

export const article = {
  author: 'Samuel Su',
  date: '2025-08-09',
  title: `GPT-5 Family and Claude Opus 4.1 Now Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['GPT-5', 'Claude Opus 4.1', 'AI Models', 'OpenAI', 'Anthropic'],
  thumbnail,
  preview: `We're excited to announce the availability of OpenAI's GPT-5 model family and Anthropic's Claude Opus 4.1 on Chat Data. These advanced models bring superior conversation quality and improved capabilities to your customer support chatbots.

## New Models

- **GPT-5**: Most advanced model with exceptional accuracy and reduced hallucinations
- **GPT-5 Mini**: Balanced performance at reduced cost for everyday support
- **GPT-5 Nano**: Ultra-fast responses for high-volume customer interactions
- **Claude Opus 4.1**: Latest Opus with enhanced reasoning and research capabilities

## Key Improvements for Chatbots

- **Better Customer Understanding**: More accurate interpretation of customer queries
- **Reduced Errors**: Significantly fewer incorrect or misleading responses
- **Faster Response Times**: Especially with GPT-5 Nano for real-time support
- **Improved Context Handling**: Better conversation flow and memory retention

All models are now available in your Chat Data model selector.`,
};


We're excited to announce the availability of OpenAI's GPT-5 model family and Anthropic's Claude Opus 4.1 on Chat Data. These advanced models bring superior conversation quality and improved capabilities to your customer support chatbots.

## New Models

- **GPT-5**: Most advanced model with exceptional accuracy and reduced hallucinations
- **GPT-5 Mini**: Balanced performance at reduced cost for everyday support
- **GPT-5 Nano**: Ultra-fast responses for high-volume customer interactions
- **Claude Opus 4.1**: Latest Opus with enhanced reasoning and research capabilities

## Key Improvements for Chatbots

- **Better Customer Understanding**: More accurate interpretation of customer queries
- **Reduced Errors**: Significantly fewer incorrect or misleading responses
- **Faster Response Times**: Especially with GPT-5 Nano for real-time support
- **Improved Context Handling**: Better conversation flow and memory retention

All models are now available in your Chat Data model selector.

GPT-5 Family and Claude Opus 4.1 Now Available

export const article = {
  author: 'Samuel Su',
  date: '2025-07-14',
  title: `WhatsApp Web Integration - Connect Your Personal WhatsApp`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['whatsapp', 'integration', 'webapi', 'ai', 'automation'],
  thumbnail,
  preview: `We're thrilled to announce WhatsApp Web integration, allowing you to connect your personal WhatsApp account to Chat Data's AI chatbot. This groundbreaking feature enables automated responses through your own WhatsApp number with simple QR code authentication.

## Key Highlights

### Personal Account Integration
- **👤 Personal Account**: Use your own WhatsApp number for business automation
- **📱 Phone Connected**: Direct integration with your mobile WhatsApp
- **⚡ Instant Setup**: Connect in seconds with QR code scanning
- **🤝 Works Together**: Seamlessly integrates with existing Chat Data features

### Advanced Configuration
- Choose between text, audio, or mixed response formats
- Configure automatic AI pause (up to 1 week) when offline
- Set response delays for more natural conversations
- Enable follow-up messages for better engagement

### Security & Reliability
- Automatic disconnect notifications via email
- Phone number blocking/allowlisting capabilities
- Real-time connection status monitoring
- Graceful handling of connection interruptions`,
};


We're thrilled to announce WhatsApp Web integration, allowing you to connect your personal WhatsApp account to Chat Data's AI chatbot. This groundbreaking feature enables automated responses through your own WhatsApp number with simple QR code authentication.

## What's New

### Personal WhatsApp Integration
Connect your personal WhatsApp account directly to Chat Data, enabling AI-powered responses without requiring WhatsApp Business API. This feature is perfect for:
- Small businesses and entrepreneurs
- Freelancers and consultants
- Teams wanting quick WhatsApp automation
- Anyone seeking to automate WhatsApp responses

### Simple QR Code Setup
Getting started is incredibly easy:
1. Navigate to **Dashboard > [Chatbot] > Integrations**
2. Select **WhatsApp Web API** integration
3. Click **Generate QR Code**
4. Open WhatsApp on your phone:
   - Android: Tap Menu (⋮) → Linked Devices
   - iPhone: Tap Settings → Linked Devices
5. Tap **Link a Device** and scan the QR code
6. Your WhatsApp is now connected!

### Configuration Options

#### Response Formats
- **Text Responses**: Standard text-based replies
- **Audio Responses**: Voice messages using AI text-to-speech
- **Mixed Responses**: Combination of text and audio based on context

#### Automatic AI Pause
Configure the chatbot to automatically pause when you're offline:
- Set pause duration from 1 hour to 1 week
- Receive email notifications for messages during pause
- Manual override available anytime

#### Response Delay
Add natural delays between messages:
- Configure delays from 0 to 60 seconds
- Creates more human-like conversation flow
- Prevents overwhelming recipients with instant responses

#### Follow-up Messages
Enable automated follow-ups when conversations go idle:
- Customizable follow-up timing
- Intelligent context-aware messages
- Helps re-engage inactive conversations

### Security Features

#### Phone Number Management
- **Blocklist**: Prevent specific numbers from receiving automated responses
- **Allowlist**: Restrict automation to approved numbers only
- **Security Dashboard**: Monitor and manage connected numbers

#### Connection Monitoring
- Real-time connection status in dashboard
- Automatic disconnect detection
- Email notifications for connection issues
- Graceful reconnection handling

### Important Considerations

⚠️ **Unofficial Integration Notice**
- This uses WhatsApp Web, not the official Business API
- Not officially supported by WhatsApp
- We implement best practices to minimize risks
- Consider WhatsApp Business API for guaranteed compliance

This integration represents our commitment to making AI automation accessible to everyone, regardless of business size. Start connecting with your customers on WhatsApp today!

WhatsApp Web Integration - Connect Your Personal WhatsApp

export const article = {
  author: 'Samuel Su',
  date: '2025-07-02',
  title: `Web Scraper AI Action Launch`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['AI-Actions', 'Web-Scraping', 'URL-Extraction', 'Content-Analysis', 'Automation'],
  thumbnail,
  preview:
    `
Introducing the **Web Scraper AI Action** - Extract and analyze content from specific URLs in real-time!

## ⚡ Key Features
- **URL-Specific Extraction** - Extract content from any webpage URL provided by users
- **Real-time Analysis** - Process and analyze webpage content instantly  
- **Intelligent Processing** - Handle complex HTML structures and extract meaningful content
- **Multi-format Support** - Works with various webpage types and content formats

## 🔥 Perfect For
- Analyzing competitor pricing pages
- Extracting product information
- Summarizing blog articles and documentation
- Getting real-time webpage content analysis

## 🌍 Platform Support
Available across all integrations including Web Widgets, WhatsApp, Messenger, Instagram, Discord, and Slack.
`,
};


We're excited to introduce the **Web Scraper AI Action**, a powerful new addition to our AI Actions suite that enables your chatbot to extract and analyze content from specific URLs in real-time!

---

## ⚡ **What is the Web Scraper AI Action?**

The Web Scraper AI Action allows your AI agent to extract content from specific webpages when users provide complete URLs. Unlike our Web Search action that finds information across the internet, this action focuses on extracting and analyzing content from the exact webpage URL provided by the user.

---

## 🚀 **Key Capabilities**

✅ **URL-Specific Content Extraction** – Extract content from any webpage URL provided by users  
✅ **Real-time Processing** – Analyze webpage content instantly for up-to-date information  
✅ **Intelligent Content Parsing** – Handle complex HTML structures and extract meaningful text  

---

## 💡 **Perfect Use Cases**

🔍 **Competitor Analysis**  
*"What does https://competitor.com/pricing say about their plans?"*

📚 **Documentation Review**  
*"Summarize the information at https://docs.example.com/getting-started"*

📰 **Article Analysis**  
*"Tell me what's in this blog post: https://blog.example.com/latest-update"*

🛍️ **Product Information**  
*"Get me the features listed on https://example.com/product-page"*

📊 **Report Extraction**  
*"Extract the key points from https://company.com/annual-report"*

---

## 🔧 **How It Works**

1. **User Provides URL**: Users include a complete URL (starting with http:// or https://) in their message
2. **Content Extraction**: The AI agent fetches and processes the webpage content
3. **Intelligent Analysis**: Extracted content is analyzed and contextualized
4. **Structured Response**: The AI provides relevant information based on the webpage content

---

## ⚠️ **Technical Specifications**

- **URL Requirement**: Complete URLs starting with http:// or https://
- **Page Size Limit**: Up to 10MB per webpage
- **Processing Timeout**: 15-second timeout for reliability

---

## 🆚 **Web Scraper vs. Web Search**

**Use Web Scraper when:**
- You have a specific URL to analyze
- You want content from an exact webpage
- Users provide direct links in their messages

**Use Web Search when:**
- You need to find information with queries
- Users ask general questions like "best practices for X"
- You want to search across multiple websites

---

Web Scraper AI Action Launch

export const article = {
  author: 'Samuel Su',
  date: '2025-06-30',
  title: 'Agent can now trigger appointments automatically',
  avatar: '/images/samuel_su_profile.png',
  thumbnail,
  hashtags: ['AI Actions', 'Appointments', 'Calendly', 'Cal.com', 'Automation'],
  preview: `We've added a new AI action that enables agents to trigger the appointment booking interface based on conditions specified in the base prompt. This update allows precise control over when and how the appointment scheduling UI is presented to users.

### Key Points

- Simple configuration through AI actions
- Customizable triggering conditions in base prompt
- Support for both Calendly and Cal.com integrations
- Web-based AI agent compatibility`,
};


# Agent can now trigger appointments automatically

We've added a new AI action that enables our agents to trigger the appointment booking interface based on specific conditions defined in your base prompt.

## About This Update

### New AI Action Overview
- Create and configure the appointment action in AI actions
- Set custom triggering conditions in your base prompt
- Integration with Calendly and Cal.com booking interfaces
- Available in web-based AI agents

### Supported Platforms
The appointment triggering action supports:
- **Calendly**: Full integration with booking modal
- **Cal.com**: Complete scheduling interface
- Currently available in web-based AI agents only

## How It Works

### Setting Up the Action
1. Create the appointment action in your AI actions
2. Connect it to your preferred scheduling platform (Calendly or Cal.com)
3. Configure the triggering conditions in your base prompt

### Base Prompt Configuration
In your base prompt, you can specify exactly when the appointment UI should be triggered:
- Define specific conditions for offering appointments
- Set precise triggering criteria
- Control how and when scheduling is presented to users

### Example Use Cases
The appointment UI can be triggered based on conditions you define, such as:
- When specific topics are discussed
- At particular points in the conversation flow
- Under certain business conditions
- Based on user request patterns

## Current Capabilities and Limitations

### What's Supported
- Web-based AI agent implementation
- Full-screen booking modal
- Direct integration with scheduling platforms
- Custom triggering conditions

### Platform Limitations
- UI triggering is currently web-only
- Must be configured through base prompt settings

## Future Plans

### Upcoming Cal.com OAuth 2.0 Integration
We're working on expanding the capabilities with:
- Text-based appointment scheduling
- Direct API integration with Cal.com
- Enhanced automation features

### Custom Integration Options
For specialized needs:
- Custom API endpoints will be available
- Text-based appointment actions
- More flexible integration options

Agent can now trigger appointments automatically

export const article = {
  author: 'Samuel Su',
  date: '2025-06-29',
  title: `Claude 4.0 Sonnet and Opus Launch`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['AI', 'LLM', 'Claude'],
  thumbnail,
  preview: `We are excited to announce the integration of Claude 4.0 Sonnet and Opus to our chatbot platform. These new models bring significant improvements in response quality, development capabilities, and chat interactions.

## Key Features

### Dual Model Support
- **Claude 4.0 Sonnet**: Our standard model, offering faster response times and improved code generation
- **Claude 4.0 Opus**: Our premium model for extended development sessions and complex tasks

### Performance Improvements
- **Enhanced Chat Experience**: Both models provide clearer, more accurate responses than previous versions
- **Better Code Generation**: Significantly improved coding capabilities compared to Claude 3.7
- **Faster Development**: Reduced response time for common development tasks

### Development Features
- **Improved Code Completion**: More accurate and contextually aware code suggestions
- **Better Error Detection**: Enhanced ability to identify and fix code issues
- **Extended Development Sessions**: Maintains context better during long coding sessions

## Upgrade Recommendation
We recommend all Claude 3.7 users upgrade to:
- **Claude 4.0 Sonnet**: For general development and chat interactions
- **Claude 4.0 Opus**: For professional development requiring extended sessions

Both models are now available in our platform's model selector, offering improved performance with the same familiar interface.`,
};


We are excited to announce the integration of Claude 4.0 Sonnet and Opus to our chatbot platform. These new models bring significant improvements in response quality, development capabilities, and chat interactions.

## Key Features

### Dual Model Support
- **Claude 4.0 Sonnet**: Our standard model, offering faster response times and improved code generation
- **Claude 4.0 Opus**: Our premium model for extended development sessions and complex tasks

### Performance Improvements
- **Enhanced Chat Experience**: Both models provide clearer, more accurate responses than previous versions
- **Better Code Generation**: Significantly improved coding capabilities compared to Claude 3.7
- **Faster Development**: Reduced response time for common development tasks

### Development Features
- **Improved Code Completion**: More accurate and contextually aware code suggestions
- **Better Error Detection**: Enhanced ability to identify and fix code issues
- **Extended Development Sessions**: Maintains context better during long coding sessions

## Upgrade Recommendation
We recommend all Claude 3.7 users upgrade to:
- **Claude 4.0 Sonnet**: For general development and chat interactions
- **Claude 4.0 Opus**: For professional development requiring extended sessions

Both models are now available in our platform's model selector, offering improved performance with the same familiar interface.

Claude 4.0 Sonnet and Opus Launch

export const article = {
  author: 'Samuel Su',
  date: '2025-06-24',
  title: 'URL & UTM Parameter Tracking Now Available',
  avatar: '/images/samuel_su_profile.png',
  thumbnail,
  hashtags: ['URL Tracking', 'UTM Parameters', 'Analytics', 'Marketing Attribution', 'User Journey'],
  preview: `We're excited to announce a powerful new feature that gives you deeper insights into how and where your chatbot is being used across your website. With URL tracking, you can now understand exactly which pages your users are engaging with your chatbot and track the source of their visits through UTM parameters.

### What's New?

- **Automatic URL Tracking**: When enabled, the system automatically captures the complete URL where users are interacting with your chatbot
- **UTM Parameter Support**: Track marketing campaign effectiveness by capturing UTM parameters from the page URL
- **Page Context Awareness**: Understand which specific pages are generating the most chatbot engagement

### How to Enable

Navigate to **Settings** > **Chat Interface** tab and enable URL tracking to start collecting valuable user journey data.`,
};


We're excited to announce a powerful new feature that gives you deeper insights into how and where your chatbot is being used across your website. With URL tracking, you can now understand exactly which pages your users are engaging with your chatbot and track the source of their visits through UTM parameters.

## What's New?

- **Automatic URL Tracking**: When enabled, the system automatically captures the complete URL where users are interacting with your chatbot
- **UTM Parameter Support**: Track marketing campaign effectiveness by capturing UTM parameters from the page URL
- **Page Context Awareness**: Understand which specific pages are generating the most chatbot engagement

## How to Enable

1. Navigate to **Settings > Chat Interface** tab
2. Look for the URL tracking toggle
3. Enable the feature to start collecting URL data

## Benefits

- **Better Analytics**: Understand which pages drive the most chatbot engagement
- **Marketing Attribution**: Track which marketing campaigns are leading to chatbot interactions
- **User Journey Insights**: Get context about where users are when they start chat conversations

## Use Cases

- Track which blog posts generate the most chatbot questions
- Measure the effectiveness of marketing campaigns in driving chatbot engagement
- Identify high-engagement pages for optimizing chatbot placement

## Privacy Note

URL tracking respects user privacy and only collects URL data from pages where your chatbot is explicitly embedded. No additional user data is collected beyond what's already present in the URL.

---

We're constantly working to improve your experience with Chat Data. If you have any questions about this feature or need help setting it up, please don't hesitate to reach out to our support team.

URL & UTM Parameter Tracking Now Available

export const article = {
  author: 'Samuel Su',
  date: '2025-06-20',
  title: 'Enhanced Theme Control: Light/Dark Mode Selection',
  avatar: '/images/samuel_su_profile.png',
  thumbnail,
  hashtags: ['Theme Control', 'Dark Mode', 'Light Mode', 'User Experience', 'Customization'],
  preview: `We're excited to announce a major enhancement to our chatbot widget's theme control system. This update provides more flexibility and better user experience when it comes to managing light and dark modes in your embedded chatbot.

### What's New?

- **Fixed Theme Mode**: Continue using fixed light or dark mode as before
- **Automatic System Theme**: Chatbot automatically adapts to your users' system preferences
- **User Theme Selection**: New menu button allows users to manually switch between themes
- **Programmatic Control**: New SDK methods for dynamic theme management`,
};


# Enhanced Theme Control: Light/Dark Mode Selection

We're excited to announce a major enhancement to our chatbot widget's theme control system. This update provides more flexibility and better user experience when it comes to managing light and dark modes in your embedded chatbot.

## What's New?

### 1. Fixed Theme Mode
- Continue using fixed light or dark mode as before
- Perfect for websites with consistent theming requirements

### 2. Automatic System Theme Detection
- Chatbot now automatically adapts to your users' system preferences
- Seamlessly switches between light and dark mode based on user's device settings
- Provides a native feel that matches the user's preferred experience

### 3. User Theme Selection
- New menu button in the chatbot widget
- Allows users to manually switch between light and dark modes
- Your chosen theme serves as the default setting

## Programmatic Theme Control

We've introduced new SDK methods to programmatically control the chatbot's theme:

```javascript
// Set specific theme
window.chatbot.setTheme('light') // or 'dark'

// Toggle between themes
window.chatbot.toggleTheme()
```

These methods enable you to:
- Synchronize the chatbot's theme with your website's theme
- Create custom theme-switching experiences
- Implement dynamic theme changes based on user interactions

## Implementation

To implement these new theme features, you can:

1. **Fixed Theme**: Set your preferred theme in the chatbot configuration
2. **System Theme**: Enable system theme detection in your settings
3. **User Selection**: The theme selection menu is automatically included in the widget

## Benefits

- **Better User Experience**: Users can now choose their preferred theme
- **System Integration**: Seamless adaptation to system preferences
- **Developer Flexibility**: Programmatic control for custom implementations
- **Consistent Branding**: Maintain visual consistency across different user preferences

We're confident these new theme control features will enhance the user experience of your embedded chatbot while providing you with more flexibility in implementation.

Enhanced Theme Control: Light/Dark Mode Selection

export const article = {
  author: 'Samuel Su',
  date: '2025-06-13',
  title: `Introducing Auto Close with Survey!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['auto close', 'survey', 'feedback', 'analytics', 'conversation management', 'customer satisfaction', 'automation'],
  thumbnail,
  preview:
    `
We're excited to announce **Auto Close with Survey** - a powerful new feature that automatically manages conversation lifecycles while gathering valuable customer feedback to help you improve your support quality.

### 🌟 What's New?  

- 🔹 **Automated Conversation Management** – Conversations automatically close after a configurable number of days (3, 7, or 14 days) following the last agent message, keeping your chat records organized.  
- 🔹 **Customer Feedback Collection** – Send customizable survey emails before closing conversations to gather customer satisfaction ratings.  
- 🔹 **Intelligent Targeting** – Limit surveys to conversations involving human agents only, conserving email credits while focusing on interactions where feedback matters most.  
- 🔹 **Customizable Survey Emails** – Fully personalize email subject lines and content with dynamic template variables including customer name, rating widget, conversation preview, and direct conversation links.  
- 🔹 **Integrated Analytics** – Survey results automatically appear in conversation records and analytics dashboards with rating distribution charts and trend analysis.  

### 📌 How to Get Started?  
Navigate to **Settings > Live Chat > Enable Auto Close** to configure your auto-close settings and customize your survey email templates. Use the test email feature to preview your surveys before going live!  

✅ **Streamlined Operations**: Reduce manual conversation management tasks  
✅ **Actionable Insights**: Gather customer satisfaction data to identify improvement opportunities  
✅ **Cost Optimization**: Smart targeting options help conserve email credits  

This feature helps you maintain organized chat records while gathering valuable insights to continuously improve your customer support experience! 🚀  
`,
};


We're excited to announce **Auto Close with Survey** - a powerful new feature that automatically manages conversation lifecycles while gathering valuable customer feedback to help you improve your support quality.

### 🌟 What's New?  

- 🔹 **Automated Conversation Management** – Conversations automatically close after a configurable number of days (3, 7, or 14 days) following the last agent message, keeping your chat records organized.  
- 🔹 **Customer Feedback Collection** – Send customizable survey emails before closing conversations to gather customer satisfaction ratings.  
- 🔹 **Intelligent Targeting** – Limit surveys to conversations involving human agents only, conserving email credits while focusing on interactions where feedback matters most.  
- 🔹 **Customizable Survey Emails** – Fully personalize email subject lines and content with dynamic template variables including customer name, rating widget, conversation preview, and direct conversation links.  
- 🔹 **Integrated Analytics** – Survey results automatically appear in conversation records and analytics dashboards with rating distribution charts and trend analysis.  
- 🔹 **Test Email Functionality** – Preview survey emails before activation to ensure perfect formatting and content.  

### 📌 How to Get Started?  
Navigate to **Settings > Live Chat > Enable Auto Close** to configure your auto-close settings and customize your survey email templates. Use the test email feature to preview your surveys before going live!  

✅ **Streamlined Operations**: Reduce manual conversation management tasks  
✅ **Actionable Insights**: Gather customer satisfaction data to identify improvement opportunities  
✅ **Cost Optimization**: Smart targeting options help conserve email credits  
✅ **Brand Consistency**: Fully customizable email templates maintain your brand voice  
✅ **Data-Driven Decisions**: Integrated analytics help measure support quality trends  

This feature enhances your customer support workflow by making it easier than ever to **maintain organized conversations while gathering valuable feedback** from your customers.  

📖 **For detailed setup instructions and configuration options, check out our [comprehensive documentation](https://cookbook.chat-data.com/docs/live-chat-escalation#auto-close-with-survey).**

**Start setting up Auto Close with Survey today!** 🚀

Introducing Auto Close with Survey!

export const article = {
  author: 'Samuel Su',
  date: '2025-06-05',
  title: `Introducing Customizable Input Limits Controls`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['input limits', 'file upload', 'user context', 'credit system', 'chatbot customization', 'SDK integration', 'batch processing', 'technical documentation'],
  thumbnail: thumbnail,
  preview: `We're excited to announce our new Customizable Input Limits Controls feature! This powerful update allows you to:

**What's New:**
- **Text Input**: Increase from 8,000 to 80,000 characters
- **File Uploads**: Upload up to 49 files per message
- **User Information**: Control truncation for SDK integrations

**Benefits:**
- Handle larger inputs while maintaining sustainable pricing
- Transparent credit-based system with real-time cost estimation
- Detailed credit consumption logging in chat logs

**Perfect For:**
- Technical documentation processing
- Multi-file batch analysis
- Applications requiring extensive user context

Ready to break free from input limits? Head to your chatbot settings and find the new **Limits Control** section to get started!`,
};


Ever struggled with the rigid input limits of our chatbot? We know that some use cases require more flexibility - whether it's processing lengthy technical documentation, handling multiple files, or sending extensive user context via our SDK.

**The Old Way: Too Restrictive** 😓

Previously, our chatbot widget was limited to:
- 8,000 characters per message
- 3 files per message
- 4,000 characters of user information

These fixed limits worked well for most use cases but held back applications that needed more flexibility.

**Introducing Customizable Input Controls!** 💡

With our latest update, we're giving you the power to handle larger inputs while maintaining sustainable pricing through a transparent credit system.

### Key Features & Benefits:

* **Text Input Freedom:**
    * Break free from the 8,000 character limit
    * Set your own limit up to 80,000 characters
    * Perfect for technical documentation and detailed reports

* **File Upload Flexibility:**
    * Move beyond the 3-file restriction
    * Upload up to 49 files in a single message
    * Ideal for batch processing and multi-file analysis

* **User Information Control:**
    * Take charge of user information truncation
    * Choose between automatic truncation or unlimited user info
    * Essential for SDK integrations requiring extensive context

* **Transparent Credit System:**
    * Messages within default limits: Standard credit cost
    * Messages exceeding limits: Proportional credit calculation
    * Credit estimation before sending
    * Detailed credit cost breakdown in chat logs debugging

### Getting Started:

Ready to break free from input limits? Here's how:

1. Go to your chatbot settings
2. Find the new **Limits Control** section
3. Adjust your desired limits:
   - Text input character limit
   - Maximum files per message
   - User information truncation settings
4. Use the credit calculator to preview costs
5. Save your settings and start sending larger messages!

### Perfect For:

* Technical documentation processing
* Legal document analysis
* Multi-file batch processing
* Applications requiring extensive user context
* Organizations needing flexible input handling
* Use cases requiring detailed logging and tracking

---

We're excited to see how you'll use these new capabilities to push the boundaries of what's possible with your chatbot. Remember, with great power comes great responsibility – use these features wisely, and always keep an eye on your credit usage!

Introducing Customizable Input Limits Controls

export const article = {
  author: 'Samuel Su',
  date: '2025-05-27',
  title: `Pinpoint AI Inaccuracies with Advanced Debugging!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['AI Debugging', 'Response Analysis', 'Knowledge Base', 'Context Sources', 'Production Debugging'],
  thumbnail,
  preview: `
**Precision Debugging:**
- See exact knowledge base snippets and data points used for each AI response
- Review sequence of AI actions (API calls, functions executed) 
- Eliminate guesswork with clear production data trails

**Rapid Issue Resolution:**
- Quickly identify outdated knowledge base content
- Spot broken links and API failures instantly
- Distinguish between model hallucination vs. context issues

**Click to Reveal:**
- All debugging information easily accessible for any production response
- Available for both text chat and voice-to-voice interactions

Stop guessing and start *knowing* exactly why your AI responded the way it did!`,
};


Ever wondered *why* your AI chatbot gave a specific, perhaps not-so-accurate, response? We know that building a highly accurate AI chatbot relies on a precise and up-to-date knowledge base. Identifying exactly what information (or misinformation!) led to a problematic AI response is crucial for improvement.

**The Old Way: Time-Consuming & Unreliable** 😓

Previously, debugging meant:
* Manually copying entire conversations into a playground.
* Trying to reproduce the exact AI response (which wasn't always possible!).
* Guessing at the sources and AI actions that might have caused the issue.

This process was often frustrating, time-consuming, and didn't always lead to a clear answer.

**Introducing a Smarter Way to Debug!** 💡

With our latest update, we're revolutionizing how you debug your AI's responses! We now **capture and store the original context sources and the specific AI actions** used to generate *every production AI response*.

### Key Features & Benefits:

* **Precision Debugging:**
    * Instantly see the exact knowledge base snippets, documents, or data points the AI used to formulate its answer.
    * Review the sequence of AI actions (e.g., API calls made, functions executed) that contributed to the response.
* **Eliminate Guesswork:**
    * No more wondering if the issue is an outdated knowledge base, a broken image URL, a misconfigured API, or the AI model itself hallucinating.
    * The production data provides a clear trail, directly pointing you to the root cause.
* **Rapid Issue Resolution:**
    * **Outdated Knowledge Base?** Quickly identify the old information and update it.
    * **Broken Links?** See the problematic URL the AI tried to use.
    * **Model Hallucination?** Understand if the context was correct but the model still erred, helping you fine-tune prompts or model settings.
    * **API Failures?** Verify if your external API endpoints are responding as expected.
* **Proactive Improvements:**
    * By understanding *why* an error occurred in production, you can make targeted fixes to your knowledge base, integrations, or AI configuration, preventing similar issues in the future.
* **Click to Reveal:**
    * All this critical debugging information is now easily accessible. Simply click to reveal the underlying sources and actions for any production AI response.


Once clicked, you'll see detailed information about the AI's decision-making process:


### Consistent Debugging Across All Interactions:

This powerful debugging capability is available for **both text-based AI chatting and our real-time voice-to-voice interactions!** No matter how your users are interacting, you have the tools to understand and improve your AI's performance.

---

Stop guessing and start *knowing*. This new debugging feature empowers you to build more accurate, reliable, and trustworthy AI chatbots faster than ever before.

Dive in and experience the clarity of precise AI debugging!

Pinpoint AI Inaccuracies with Advanced Debugging!

export const article = {
  author: 'Samuel Su',
  date: '2025-05-24',
  title: `Enhanced Chatbot Security with User Authentication!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['User Authentication', 'Security', 'SDK Integration', 'Access Control', 'Chatbot Security'],
  thumbnail,
  preview: `We're excited to introduce a powerful new security feature for your chatbots: User Authentication. This update allows you to ensure that only verified users can interact with your chatbot when embedded via our SDK.

### 🔐 Key Features

- **Secure User Verification**: Verify user identity before chat sessions begin
- **Server-Side Security**: Hash generation ensures maximum security  
- **Access Control**: Control access to sensitive information and functionalities
- **SDK Integration**: Seamless integration with your existing user system

### 💪 Capabilities
- userId and userHash parameters for authenticated users
- Secret key-based authentication (server-side only)
- Public URL access disabled when enabled
- SDK-only access with mandatory authentication

### 🚀 Enhanced Security
- No more unauthorized access to your chatbot
- Complete control over who can interact with your AI
- Perfect for protecting sensitive chatbots and ensuring only verified users can access your AI assistant

For implementation details, check our [documentation](https://cookbook.chat-data.com/docs/logged-in-user-experience#user-authentication).`,
};


We're excited to introduce a powerful new security feature for your chatbots: **User Authentication**. This update allows you to ensure that only verified users can interact with your chatbot when embedded via our SDK, adding a crucial layer of security and control.

### 🔐 Why User Authentication?

In many scenarios, you need to ensure that sensitive information or specific functionalities are accessible only to logged-in or known users. Our new User Authentication feature makes this possible by verifying user identity before a chat session can begin.

### ⚙️ How It Works

For secure integration with authenticated users, our SDK now supports two special parameters:

- **userId**: A unique identifier for the user (up to 30 characters).
- **userHash**: A security hash generated on your server to validate the user's identity (up to 100 characters).

### 🛡️ Key Security Implementation

**Server-Side userHash Generation:** To maintain the integrity of the authentication process, the **userHash** **MUST** be generated on your server using a secret key provided by us. **Never generate this hash on the client-side or expose your secret key in client-side code.**

### 🚀 Enabling User Authentication

1. Navigate to **Settings > Security** tab in your Chat Data dashboard.
2. Turn on the **User Authentication** toggle.
3. Once enabled, you'll be provided with a unique **Secret Key for User Authentication**. Use this key on your server to generate the **userHash**.

### ⚠️ Important Changes When Enabled

Activating User Authentication brings important changes to how users can access your chatbot:

- ⛔ **No More Direct Public URL Access:** Chatting directly with your chatbot via its public URL will be **rejected**.
- ✅ **SDK Authentication Required:** Users **must** interact with your chatbot through either the **chatbot widget** or **iframe embedding** methods.
- 🔑 **Mandatory SDK Parameters:** Your frontend implementation using our SDK must send the correct **userId** and the server-generated **userHash** to the chatbot to initiate a conversation.
- 🚫 **Access Denied Without Authentication:** Any attempts to chat without proper **userId** and **userHash** will be rejected, safeguarding your chatbot.

---

Secure your chatbot interactions and gain greater control over who accesses your AI. Enable User Authentication today to add an essential security layer to your chatbot deployments!

For more details, please refer to our [documentation](https://cookbook.chat-data.com/docs/logged-in-user-experience#user-authentication).

Enhanced Chatbot Security with User Authentication!

export const article = {
  author: 'Samuel Su',
  date: '2025-05-20',
  title: `Prestashop Integration: Seamless Product Importing & Real-Time Sync`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['Prestashop', 'E-commerce', 'Product Import', 'Real-time Sync', 'Webhook Integration'],
  thumbnail,
  preview: `## 🛍️ New Prestashop Integration Features

**Direct Product Importing:**
- Connect your Prestashop store using Webservice API
- Import entire product catalog with one click
- Secure, read-only access with granular permissions

**Real-Time Sync via Webhook:**
- Install our Prestashop webhook module
- Automatic updates for product changes, creations, and deletions
- Always current chatbot with latest product information

Say goodbye to manual data entry and ensure your AI chatbot provides customers with up-to-date product details for better interactions and more sales!`,
};


We're thrilled to announce powerful new features for our Prestashop users! Now you can effortlessly connect your Prestashop store to our platform, enabling streamlined product importing and automatic real-time synchronization. Say goodbye to manual data entry and hello to an always up-to-date product catalog for your AI chatbot!

This integration comes in two powerful parts:

## 🛍️ **Part 1: Direct Prestashop Product Importing**

Easily bring your entire Prestashop product catalog into our system with our new direct importer.

### Key Features & Benefits:

* **Effortless Setup:**
    * **Enable Webservice API:** Quickly enable Prestashop's Webservice and generate a dedicated API key.
    * **Secure Access:** We use your Webservice key *only* for product importing and **do not store it**, ensuring your store's security.
    * **Granular Permissions:** You grant specific read-only (GET) access to necessary product-related resources, giving you full control.
* **Simple Import Process:**
    * Navigate to **Sources > Product**.
    * Select "Prestashop Store Domain."
    * Enter your Prestashop webservice main entry point and the generated API key.
    * Click **Import** - and that's it!
* **Data Accuracy & Control:**
    * **Detailed View:** Preview all imported product information (e.g., attachments, categories, combinations, images, prices, stock levels, etc.).
    * **Easy Corrections:** If you spot any discrepancies, simply correct them in your Prestashop admin panel and re-import.
    * **Selective Importing:** Remove any unwanted products before training your chatbot, ensuring only relevant items are included.
* **Enhanced Chatbot Training:**
    * Once verified, click **Create/Retrain Chatbot** to train your agent with accurate and comprehensive product data.

**Benefit:** Save significant time and effort by directly importing your Prestashop products. Ensure your chatbot is trained on the most accurate and complete product information from the get-go, leading to better customer interactions and more sales.

---

## 🔄 **Part 2: Real-Time Prestashop Product Sync via Webhook Module**

Keep your chatbot's product knowledge instantly updated with our new Webhook Synchronization feature. Any changes in your Prestashop store - product updates, creations, or deletions - will automatically reflect in our system.

### Key Features & Benefits:

* **Automated Updates:**
    * **Install Our Module:** Download and install the "Chat Data Webhook module for Prestashop" via your Prestashop admin panel (Modules > Module Manager > Upload a module).
    * **Automatic Triggers:** Once configured, product changes in your store automatically send webhook events to our platform.
* **Simple Configuration:**
    * **Get Your Webhook URL:** In our platform, navigate to the **Integrations** tab in your chatbot menu and click **Integrate with Prestashop** to get a unique webhook URL.
    * **Link Chat Data & Prestashop:**
        * Paste the copied webhook URL into the "Chat Data Webhook module" configuration in your Prestashop admin.
        * Copy the webhook secret *from* the "Chat Data Webhook module" *to* the Prestashop integration modal in our platform.
* **Reliable Synchronization:**
    * **Test Event Sending:** Easily send a test event for any product ID from your Prestashop store to ensure the connection is working correctly (look for a 200 status code and success message).
* **Always Current Chatbot:**
    * Your chatbot will always have the latest product information (new arrivals, stock changes, price updates, discontinued items) without manual intervention.

**Benefit:** Ensure your chatbot provides customers with the most current product details, reducing errors, improving customer satisfaction, and preventing lost sales due to outdated information. Your chatbot becomes a truly dynamic and reliable extension of your Prestashop store.

---

Ready to supercharge your e-commerce AI? Head over to your account and explore these new Prestashop integration features today!

For detailed setup instructions, please refer to our documentation:
* **Direct Prestashop Products Importing:** [https://cookbook.chat-data.com/docs/train-with-your-data#prestashop](https://cookbook.chat-data.com/docs/train-with-your-data#prestashop)
* **Realtime Prestashop Products Sync:** [https://cookbook.chat-data.com/docs/chatbots-real-time-products-update#prestashop-webhook-synchronization-integration](https://cookbook.chat-data.com/docs/chatbots-real-time-products-update#prestashop-webhook-synchronization-integration)

Happy Integrating!

Prestashop Integration: Seamless Product Importing & Real-Time Sync

export const article = {
  author: 'Samuel Su',
  date: '2025-05-10',
  title: `Mandatory Privacy Consent Modal`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['privacy', 'consent', 'compliance', 'gdpr'],
  thumbnail,
  preview: `
Introducing **Mandatory Privacy Consent Modal** - Enhanced user privacy control and regulatory compliance.

### Key Features

- **Explicit Consent:** Require users to actively consent to privacy terms before chatbot interaction
- **Customizable Content:** Tailor consent messaging to match your privacy policy requirements
- **Compliance Ready:** Meet GDPR, CCPA, and other privacy regulations with documented user consent
- **Easy Setup:** Enable via **Settings** > **Privacy Consent** with fully customizable content and styling

This feature transforms passive privacy disclaimers into active consent collection, ensuring users explicitly agree to your data processing terms before engaging with your AI chatbot.
`,
};


**Mandatory Privacy Consent Modal Launch!**

We're excited to introduce our new **Mandatory Privacy Consent Modal** feature, providing stronger privacy controls and helping you meet regulatory compliance requirements. Now, instead of relying on passive privacy disclaimers at the bottom of your chatbot, you can require users to explicitly consent to your privacy terms before interacting with your AI assistant.

### What's New?

- **Active Consent Collection:**  
  The new privacy consent modal appears before users can interact with your chatbot, requiring them to explicitly click to agree with your privacy policy and data collection practices. Users who decline consent will not be able to proceed with using the chatbot.


- **Easy Setup:**  
  Enable the Mandatory Privacy Consent Modal by navigating to the **Privacy Consent** section under **Settings** and toggling on the feature. You can customize the consent message, button text, and privacy policy link to align with your specific requirements.


- **Full Customization Options:**  
  - **Consent Message:** Craft a clear explanation of how user data will be collected and used
  - **Accept/Reject Buttons:** Customize text for both consent and decline buttons
  - **Privacy Policy Link:** Add a direct link to your detailed privacy policy with custom link text
  - **Cookie Expiry:** Set how long the consent should be remembered (1-365 days)
  - **Theme Compatibility:** Works seamlessly with both light and dark themes


### Benefits of Explicit Privacy Consent

- **Enhanced Regulatory Compliance:**  
  Meet the requirements of GDPR, CCPA, and other privacy regulations that mandate explicit, informed consent before collecting and processing user data.

- **Improved User Trust:**  
  Demonstrate your commitment to transparency and user privacy by clearly communicating how user data will be handled and requiring active opt-in.

- **Risk Mitigation:**  
  Reduce legal and compliance risks by maintaining clear records of user consent and providing an explicit rejection option.

- **Seamless User Experience:**  
  The modal is designed to present privacy information clearly without overwhelming users, with responsive design that works across all devices.

### Implementation Details

- Consent is stored as a browser cookie, with a configurable expiry period
- Modal automatically adapts to your chatbot's theme settings (light/dark)
- Consent must be provided for each new conversation or when cookies expire
- External links open in new tabs for easy reference without disrupting the chat flow

This feature transforms passive privacy notifications into active consent collection—ensuring users explicitly agree to your terms before engaging with your AI chatbot.

**Happy Privacy-Compliant Chatting!**

Mandatory Privacy Consent Modal

export const article = {
  author: 'Samuel Su',
  date: '2025-05-07',
  title: `Live Chat Notifications Now Available in 30 Languages`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['localization', 'notifications', 'multi-language', 'email', 'sms'],
  thumbnail,
  preview: `We're excited to announce comprehensive language support for all live chat notifications! Your email and SMS notifications will now automatically be delivered in your preferred language.

## What's New

- Email and SMS notifications for live chat are now available in 30 languages
- Notifications are translated to your selected language preference
- Improved user experience for international customers
- Seamless localization across all notification types`,
};


# Live Chat Notifications Now in 30 Languages

We're excited to announce that all live chat notifications are now available in 30 languages! Whether you're receiving notifications via email or SMS, they will automatically be delivered in your preferred language.

## What's New

When a live chat is escalated or when agents respond to customers, all notification content is now fully localized, including:

- Email subject lines and body content
- SMS notification messages

## Supported Languages

All notifications now support these 30 languages:

- English (US)
- Chinese (Simplified)
- Spanish
- French
- German
- Japanese
- Portuguese (Brazil)
- Italian
- Russian
- Dutch
- Korean
- Arabic
- Turkish
- Polish
- Hindi
- Danish
- Finnish
- Vietnamese
- Hebrew
- Filipino
- Ukrainian
- Swedish
- Norwegian
- Thai
- Indonesian
- Malaysian
- Czech
- Hungarian
- Greek
- Romanian


## Benefits

- **Improved Customer Experience**: Provide support in your customers' native languages
- **Reduced Miscommunication**: Clear and accurate notifications in the preferred language
- **Higher Engagement**: Increase response rates with easily understood notifications

This update represents our commitment to creating a truly global platform that works for users everywhere, regardless of language preference.

Live Chat Notifications Now Available in 30 Languages

export const article = {
  author: 'Samuel Su',
  date: '2025-05-06',
  title: `Chat Data SDK Now Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['SDK', 'integration', 'chat data', 'web development'],
  thumbnail,
  preview: `We're excited to announce the release of our Chat Data SDK! This JavaScript library enables seamless real-time communication between your website and chatbots. Now you can easily share user data with chatbots and listen for chat events to create dynamic, personalized user experiences.`,
};


# Introducing Chat Data SDK

We're excited to announce the release of our Chat Data SDK! This JavaScript library enables seamless integration between your website and our chatbots, creating more personalized and interactive user experiences.

## Key Features

- **User Information Sharing**: Pass user data directly from your website to chatbots, eliminating redundant data collection
- **Event Listening**: Respond to chat events in real-time, including messages, lead form submissions, and live chat requests
- **Simple Integration**: Add the SDK to your site with just a single line of code

## Quick Implementation

```html
```

## Demo and Documentation

Check out our [live demo](https://www.chat-data.com/static/chatbot-sdk-demo.html) to see the SDK in action, or visit our [detailed documentation](https://cookbook.chat-data.com/docs/chatbot-sdk) to learn about all available features and implementation options.

Chat Data SDK Now Available

export const article = {
  author: 'Samuel Su',
  date: '2025-05-02',
  title: `Agent Size Limit Increased To 33/44/55 Million Characters`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['capacity increase', 'character limit', 'chatbot capacity', 'storage upgrade'],
  thumbnail,
  preview: `We're excited to announce significant increases to our per-chatbot capacity limits! Our latest update allows each agent to hold substantially more data:

## New Per-Chatbot Limits

- **Entry Plan**: 33 MB characters per chatbot
- **Standard Plan**: 44 MB characters per chatbot
- **Professional Plan**: 55 MB characters per chatbot

This update gives you greater flexibility in how you distribute your total account capacity across different chatbots, allowing for more specialized and data-rich agents.`,
};


We're excited to announce significant increases to our per-chatbot capacity limits! Our latest update allows each agent to hold substantially more data.

## New Per-Chatbot Limits

- **Entry Plan**: 33 MB characters per chatbot
- **Standard Plan**: 44 MB characters per chatbot
- **Professional Plan**: 55 MB characters per chatbot

## How It Works

While your account-level total capacity remains unchanged, you now have much more flexibility in how you allocate this capacity across your chatbots:

- **Entry Plan**: 22 MB total characters across 2 chatbot slots
- **Standard Plan**: 110 MB total characters 
- **Professional Plan**: 400 MB total characters

You can allocate your full account capacity to a single chatbot (up to the per-chatbot limit) or distribute it across multiple chatbots according to your needs.

## Additional Chatbot Slots

Need more capacity? You can subscribe to additional chatbot slots, with each add-on providing:

- 11 MB extra characters at the account level
- 1 additional chatbot slot

## Example: Entry Plan

If you're on the Entry plan, you start with:
- 22 MB total characters
- 2 chatbot slots, each with a 33 MB maximum capacity

You could allocate all 22 MB to one chatbot, leaving the second chatbot with no capacity until you increase your limit.

If you subscribe to an additional chatbot slot, you'll get:
- An extra 11 MB characters (bringing your total to 33 MB)
- One more chatbot slot

You could then allocate that full 33 MB to a single chatbot, reaching its maximum limit under the Entry plan.

## Understanding Your Capacity

A chatbot's actual capacity is always the lesser of:
1. Your remaining unused account-level character limit
2. The plan-based per-chatbot limit (33/44/55 MB)

This update gives you greater flexibility in how you distribute your total account capacity across different chatbots, allowing for more specialized and data-rich agents.

Agent Size Limit Increased To 33/44/55 Million Characters

export const article = {
  author: 'Samuel Su',
  date: '2025-04-27',
  title: `Training By Notion Pages`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['notion', 'training', 'integration'],
  thumbnail,
  preview:
    `
Train your agent with pages directly from Notion. Import content from any Notion workspace you have access to, set up automated retraining, and keep your knowledge base current with our seamless Notion integration.

## ⚡ Key Features
- **Seamless Import**: Connect to any Notion workspace you have access to
- **Smart Selection**: Import specific pages for targeted training
- **Automated Retraining**: Set up cron jobs to keep your agent updated

Start enhancing your agent with Notion integration today!
`,
};


We're excited to announce our new Notion integration! Now you can easily train your agent using pages directly from any Notion workspace you have access to.

## Key Features

- **Seamless Import**: Connect to any Notion workspace you have access to and select multiple pages with just a few clicks
- **Smart Selection**: Import specific pages for targeted training of your agent
- **Automated Retraining**: Set up daily, weekly, or monthly cron jobs to keep your agent's knowledge base updated with the latest content

## How It Works

### Import Pages From Notion

1. Navigate to the Sources tab and select Notion
2. Click the **Import from Notion** button
3. After confirmation, select the documents from your Notion workspace
4. Click the **Allow Access** button in the Notion page picker modal to begin importing
5. Review the imported content by clicking the eye icon next to each file
6. Click **Create/Retrain Chatbot** to begin training with your Notion pages

### Important Notes

- Your selection determines which Notion pages Chat Data can access across all your agents and any Chat Data accounts linked to this Notion workspace
- Always keep previously selected pages for active agents selected
- Never deselect pages that are already selected
- If you only need a subset of pages, you can delete unwanted pages after importing
- Notion access permissions may take up to 20 seconds to propagate
- If files don't appear after importing, Notion may not have fully processed the access grant
- In this case, repeat from step 2 with the same page selection, which typically resolves the issue

## Automated Retraining with Notion

Create a single cron training job that automatically retrains your agent with the latest versions of your Notion pages:

1. Navigate to the Sources tab and select Notion
2. Click the **Add Cron Training Job** button
3. Select your preferred frequency: Daily, Weekly, or Monthly
4. Click **Save** to activate the scheduled retraining

### Important Notes About Automatic Retraining

- You can create only one Notion cron job per agent
- All previously imported Notion pages will be automatically retrained at your scheduled frequency
- If a page is removed from your Notion workspace, the agent will continue using the last imported version
- To remove content from your agent's knowledge base, you must manually delete it from your sources

Read [Notion Training](https://cookbook.chat-data.com/docs/train-with-your-data#notion) for more details

Training By Notion Pages

export const article = {
  author: 'Samuel Su',
  date: '2025-04-23',
  title: `Training By Google Documents and SpreadSheets`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['Google-Drive', 'Chatbot-Training', 'Document-Import', 'Automation', 'Knowledge-Base', 'Spreadsheets', 'Integration', 'Cron-Jobs'],
  thumbnail,
  preview:
    `
Train your chatbot with Google Drive documents and spreadsheets. Import content from multiple Google accounts, set up automated retraining, and keep your knowledge base current with our seamless Google Drive integration.

## ⚡ Key Features
- **Seamless Import**: Connect to any Google Drive account you have access to
- **Multi-Account Support**: Import files from different Google Drive accounts
- **Automated Retraining**: Set up cron jobs to keep your chatbot updated

Start enhancing your chatbot with Google Drive integration today!
`,
};


We're excited to announce our new Google Drive integration! Now you can easily train your chatbot using documents and spreadsheets directly from Google Drive.

## Key Features

- **Seamless Import**: Connect to any Google Drive accounts you have access to and select multiple documents and spreadsheets with just a few clicks
- **Multi-Account Support**: Import files from different Google Drive accounts in a single workflow
- **Automated Retraining**: Set up daily, weekly, or monthly cron jobs to keep your chatbot's knowledge base updated with the latest content

## How It Works

1. Click the **Import from Google Drive** button
2. Grant access permission when prompted
3. Select your documents and spreadsheets from the Google Drive Picker
4. Train your chatbot with the imported content

The integration treats Google documents similarly to .docx files and Google spreadsheets like .csv files, maintaining all the familiar training options you're used to.

## Automated Updates

Create a single cron training job that automatically retrains your chatbot with the latest versions of your selected Google Drive files. Even if files are removed from Google Drive, your chatbot will retain previously trained content.

Read [Google Drice Training](https://cookbook.chat-data.com/docs/train-with-your-data#google-drive) for more details

Training By Google Documents and SpreadSheets

export const article = {
  author: 'Samuel Su',
  date: '2025-04-21',
  title: `n8n Integration Is Now Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['n8n integration', 'n8n', 'chat data', 'automation'],
  thumbnail,
  preview: `We're thrilled to announce the release of our official n8n integration nodes for Chat Data! This integration brings powerful automation capabilities to your Chat Data workflows.

## What's Included

The n8n-nodes-chat-data package provides a comprehensive set of nodes to interact with the Chat Data platform:

- Send messages to chatbots
- Retrieve customer leads
- Manage conversation history
- Create and train chatbots
- Update chatbot prompts
- Handle real-time chat events

Visit our [npm package page](https://www.npmjs.com/package/n8n-nodes-chat-data?activeTab=readme) for detailed documentation on installation, authentication setup, and available operations.
`,
};


We're thrilled to announce the release of our official n8n integration nodes for Chat Data! This integration brings powerful automation capabilities to your Chat Data workflows.

## What's Included

The n8n-nodes-chat-data package provides a comprehensive set of nodes to interact with the Chat Data platform:

- Send messages to chatbots
- Retrieve customer leads
- Manage conversation history
- Create and train chatbots
- Update chatbot prompts
- Handle real-time chat events

## Getting Started

You can install the integration using npm:

```shell
npm install n8n-nodes-chat-data
```

For n8n desktop app/local installation:

```shell
n8n-node-dev --install n8n-nodes-chat-data
```

Visit our [npm package page](https://www.npmjs.com/package/n8n-nodes-chat-data?activeTab=readme) for detailed documentation on installation, authentication setup, and available operations.

## Prerequisites

- A paid Chat Data account
- Your Chat Data API key (available in account settings)

Start automating your chat workflows today with our new n8n integration!

n8n Integration Is Now Available

export const article = {
  author: 'Samuel Su',
  date: '2025-04-17',
  title: `GPT-4.1, O3 and O4 Mini Models Now Available on Chat Data`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['GPT-4.1', 'O3', 'O4 Mini', 'AI Models', 'OpenAI'],
  thumbnail,
  preview: `GPT-4.1, O3 and O4 mini models are now live on Chat Data. This latest OpenAI update delivers quicker, more consistent output, enhanced logic capabilities, and improved effectiveness across numerous applications.

Access GPT-4.1 by visiting your Chat Data settings now.`,
};


GPT-4.1, O3 and O4 mini models are now live on Chat Data. This latest OpenAI update delivers quicker, more consistent output, enhanced logic capabilities, and improved effectiveness across numerous applications.

Access GPT-4.1 by visiting your Chat Data settings now.

GPT-4.1, O3 and O4 Mini Models Now Available on Chat Data

export const article = {
  author: 'Samuel Su',
  date: '2025-04-16',
  title: `Internationalization of the Chatbot Interface`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['i18n', 'multilingual', 'chatbot', 'localization', 'language support', 'global chatbot'],
  thumbnail,
  preview:
    `
We're excited to introduce **Internationalization (i18n)** — a new feature that allows your chatbot interface to automatically adapt to your users' browser language.

Previously, even if you could choose your own text or initial message in your own locale, you were bounded by that single text in the single locale only.

With internationalization, you can now customize initial messages, suggested replies, and other chatbot texts in multiple languages, providing a more personalized experience for your global audience.

To enable it, head over to **Settings** > **Chat Interface** > **Enable Internationalization (i18n)**.
`,
};


We're excited to introduce **Internationalization (i18n)** — a new feature that allows your chatbot interface to automatically adapt to your users' browser language.

Previously, even if you could choose your own text or initial message in your own locale, you were bounded by that single text in the single locale only.

With internationalization, you can now customize initial messages, suggested replies, and other chatbot texts in multiple languages, providing a more personalized experience for your global audience.

To enable it, head over to **Settings** > **Chat Interface** > **Enable Internationalization (i18n)**.

Here's a preview of the Chat Data chatbot in Spanish, Chinese, and French!


Our internationalization feature currently supports the following languages. **If you require additional language support, please reach out to our team.** We have the capability to implement virtually any locale based on your needs.
- English (United States) - en-US
- Chinese (Simplified) - zh-CN
- Spanish (Spain) - es-ES
- French (France) - fr-FR
- German (Germany) - de-DE
- Japanese (Japan) - ja-JP
- Portuguese (Brazil) - pt-BR
- Italian (Italy) - it-IT
- Russian (Russia) - ru-RU
- Dutch (Netherlands) - nl-NL
- Korean (South Korea) - ko-KR
- Arabic (Saudi Arabia) - ar-SA
- Turkish (Turkey) - tr-TR
- Polish (Poland) - pl-PL
- Hindi (India) - hi-IN
- Danish (Denmark) - da-DK
- Finnish (Finland) - fi-FI
- Vietnamese (Vietnam) - vi-VN
- Hebrew (Israel) - he-IL
- Filipino (Philippines) - fil-PH
- Ukrainian (Ukraine) - uk-UA
- Swedish (Sweden) - sv-SE
- Norwegian (Norway) - nb-NO
- Thai (Thailand) - th-TH
- Indonesian (Indonesia) - id-ID
- Malaysian (Malaysia) - ms-MY
- Czech (Czech Republic) - cs-CZ
- Hungarian (Hungary) - hu-HU
- Greek (Greece) - el-GR
- Romanian (Romania) - ro-RO

Internationalization of the Chatbot Interface

export const article = {
  author: 'Samuel Su',
  date: '2025-04-08',
  title: `Introducing AI Re-Engagement`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: [
    'ai-follow-up',
    'customer-engagement',
    'whatsapp-automation',
    'messenger-bot',
    'instagram-automation',
    'automated-messaging',
    'customer-service',
    'ai-agent',
    'business-automation',
    'conversation-ai',
    'customer-retention',
    'intelligent-follow-up',
    '24hour-response',
    'chatbot-automation',
    'social-media-automation'
  ],
  thumbnail,
  preview:
    `Introducing **AI Re-Engagement** - Our AI agent now intelligently follows up with customers on WhatsApp, Messenger, and Instagram within 24 hours based on conversation context.

## Background
Following initial customer interactions, timely follow-ups are crucial for ensuring customer satisfaction. Since manually following up with each customer isn't scalable, we've developed an AI system that intelligently manages customer re-engagement within a 24-hour window.

## How it works
You can customize three key aspects of the re-engagement:
1. The time window for follow-up after the last message
2. The specific conditions that trigger a follow-up
3. The style and content of the re-engagement message

When the specified time arrives, the AI evaluates whether the conversation meets your defined re-engagement criteria. If the conditions are met, it sends a contextually appropriate follow-up message based on the previous conversation.

## How to set up
Simply configure the time window, trigger conditions, and messaging instructions after connecting your WhatsApp, Messenger, or Instagram account with your AI agent.

`,
};


Introducing **AI Re-Engagement** - Our AI agent now intelligently follows up with customers on WhatsApp, Messenger, and Instagram within 24 hours based on conversation context.

## Background
Following initial customer interactions, timely follow-ups are crucial for ensuring customer satisfaction. Since manually following up with each customer isn't scalable, we've developed an AI system that intelligently manages customer re-engagement within a 24-hour window.

## How it works
You can customize three key aspects of the re-engagement:
1. The time window for follow-up after the last message
2. The specific conditions that trigger a follow-up
3. The style and content of the re-engagement message

When the specified time arrives, the AI evaluates whether the conversation meets your defined re-engagement criteria. If the conditions are met, it sends a contextually appropriate follow-up message based on the previous conversation.

## How to set up
Simply configure the time window, trigger conditions, and messaging instructions after connecting your WhatsApp, Messenger, or Instagram account with your AI agent.

Introducing AI Re-Engagement

export const article = {
  author: 'Samuel Su',
  date: '2025-04-07',
  title: `Gemini 2.5 is Now Available`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['gemini', 'google deepmind', 'llm', 'machine learning', 'ai model', 'natural language processing'],
  thumbnail,
  preview: `Gemini 2.5 Pro is the latest and most advanced AI model from Google DeepMind, designed to push the boundaries of intelligent problem-solving. As an experimental release in the Gemini 2.5 series, it excels in complex reasoning, advanced coding, and multimodal understanding. With top-tier performance across industry benchmarks—including math, science, and code generation—Gemini 2.5 Pro represents a significant leap forward in AI capabilities. Featuring a massive 1-million-token context window and state-of-the-art reasoning, it's built to handle the most challenging tasks across a wide range of domains.

The credit cost of Gemini 2.5 Pro is the same as Gemini 1.5 Pro. Due to the higher capabilities of Gemini 2.5 Pro at the same cost, we have deprecated the Gemini 1.5 Pro model.`,
};


Gemini 2.5 Pro is the latest and most advanced AI model from Google DeepMind, designed to push the boundaries of intelligent problem-solving. As an experimental release in the Gemini 2.5 series, it excels in complex reasoning, advanced coding, and multimodal understanding. With top-tier performance across industry benchmarks—including math, science, and code generation—Gemini 2.5 Pro represents a significant leap forward in AI capabilities. Featuring a massive 1-million-token context window and state-of-the-art reasoning, it's built to handle the most challenging tasks across a wide range of domains.

The credit cost of Gemini 2.5 Pro is the same as Gemini 1.5 Pro. Due to the higher capabilities of Gemini 2.5 Pro at the same cost, we have deprecated the Gemini 1.5 Pro model.

Gemini 2.5 is Now Available

export const article = {
  author: 'Samuel Su',
  date: '2025-04-04',
  title: `SMS Notification Support`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['sms notifications', 'twilio integration', 'customer support alerts', 'Chat Data SMS','Live chat SMS'],
  thumbnail,
  preview:
    `We're excited to announce a new way to stay connected with your customers and operators—**SMS notifications for live chat escalation**!

Now, in addition to email, webhook, and Zendesk notifications, you can send real-time SMS alerts to operators and customers. Whether it's notifying an agent about a new live chat escalation or updating a customer when their message gets a response, SMS ensures instant communication and a seamless support experience.

## Key Features:
- **Import Phone Numbers from Twilio** – Bring your Twilio numbers into Chat Data for sending and receiving SMS notifications.
- **Use Platform-Provided SMS** – No Twilio number? No problem! Use our Twilio-powered number for just $0.05 per SMS.
- **Agent SMS Alerts** – Notify up to 5 operator agents via SMS when a chat is escalated.
- **Lead SMS Notifications** – If a lead provides their phone number and opts in, they'll receive an SMS when they get a response.
- **Custom Opt-In Text** – Personalize the opt-in message in the lead form.

## How to Get Started:
1. Import your Twilio phone numbers in Settings > Phone Numbers (free).
2. Enable SMS notifications in Settings > Live Chat.
3. Choose your SMS sender (your Twilio number or our platform-provided option).
4. Set up agent receivers and lead opt-in preferences.

💡 Pro Tip: Don't have a Twilio number? You can use our platform’s Twilio number and simply purchase SMS credits via our [Pricing Page](/pricing).

This feature ensures that no lead or escalation goes unnoticed. Get started today and **enhance your live chat experience with SMS!**

[🔗 Learn More in Our Guide](https://cookbook.chat-data.com/docs/sms-notifications)`,
};


We're excited to announce a new way to stay connected with your customers and operators—**SMS notifications for live chat escalation**!

Now, in addition to email, webhook, and Zendesk notifications, you can send real-time SMS alerts to operators and customers. Whether it's notifying an agent about a new live chat escalation or updating a customer when their message gets a response, SMS ensures instant communication and a seamless support experience.

## Key Features:
- **Import Phone Numbers from Twilio** – Bring your Twilio numbers into Chat Data for sending and receiving SMS notifications.
- **Use Platform-Provided SMS** – No Twilio number? No problem! Use our Twilio-powered number for just $0.05 per SMS.
- **Agent SMS Alerts** – Notify up to 5 operator agents via SMS when a chat is escalated.
- **Lead SMS Notifications** – If a lead provides their phone number and opts in, they'll receive an SMS when they get a response.
- **Custom Opt-In Text** – Personalize the opt-in message in the lead form.

## How to Get Started:
1. Import your Twilio phone numbers in Settings > Phone Numbers (free).
2. Enable SMS notifications in Settings > Live Chat.
3. Choose your SMS sender (your Twilio number or our platform-provided option).
4. Set up agent receivers and lead opt-in preferences.

💡 Pro Tip: Don't have a Twilio number? You can use our platform’s Twilio number and simply purchase SMS credits via our [Pricing Page](/pricing).

This feature ensures that no lead or escalation goes unnoticed. Get started today and **enhance your live chat experience with SMS!**

[🔗 Learn More in Our Guide](https://cookbook.chat-data.com/docs/sms-notifications)

SMS Notification Support

export const article = {
  author: 'Samuel Su',
  date: '2025-03-22',
  title: `Customize Voices with Real-Time Voice-to-Voice Chat`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['real time voice chat', 'custom voice chat', 'elevenlabs voice', 'openai voice chat', 'voice to voice chat', 'custom ai voices'],
  thumbnail,
  preview:
    `Following the previous release of the [Customize Voices with Your Chatbot](/changelog/customize-voices-with-integrations), we are excited to extend custom voice support to real-time voice-to-voice chat. With this feature, you can replace the native voices of OpenAI with your own customized voice from ElevenLabs while still enjoying all the powerful features of OpenAI's real-time voice functionality.

## How to use it
- You can simply turn on the 'User Customize Voice' toggle in the **Realtime Voices** settings. Then, the output voices of the real-time communication will switch to your chosen voices configured in the **Customize Voices** settings, as shown below.

After enabling the feature, the output voices of the real-time communication will switch to your chosen voice while maintaining all the other features of the real-time voice-to-voice chat. Because you are using your own customized voice, users cannot select OpenAI's provided voices in the Chatbot interface anymore.
`,
};


Following the previous release of the [Customize Voices with Your Chatbot](/changelog/customize-voices-with-integrations), we are excited to extend custom voice support to real-time voice-to-voice chat. With this feature, you can replace the native voices of OpenAI with your own customized voice from ElevenLabs while still enjoying all the powerful features of OpenAI's real-time voice functionality.

## How to use it
- You can simply turn on the 'User Customize Voice' toggle in the **Realtime Voices** settings. Then, the output voices of the real-time communication will switch to your chosen voices configured in the **Customize Voices** settings, as shown below.

After enabling the feature, the output voices of the real-time communication will switch to your chosen voice while maintaining all the other features of the real-time voice-to-voice chat. Because you are using your own customized voice, users cannot select OpenAI's provided voices in the Chatbot interface anymore.

You can watch this Demo Youtube video to see the experience:

Customize Voices with Real-Time Voice-to-Voice Chat

export const article = {
  author: 'Samuel Su',
  date: '2025-03-16',
  title: `Customize Voices with Your Chatbot`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['chatbot voice customization', 'elevenlabs integration', 'custom ai voice', 'whatsapp voice bot', 'messenger voice bot', 'instagram voice bot', 'ai voice chat', 'chatbot audio responses'],
  thumbnail,
  preview:
    `We're excited to introduce custom voice support for your chatbot! Your AI can now speak with your chosen ElevenLabs voice across all platforms - from WhatsApp to your website widget.

## Key Features
- 🎯 Custom ElevenLabs voices for all chat responses
- 🔌 Works with WhatsApp, Messenger, Instagram, Slack, and Discord
- ⚡ Easy setup with API key integration
- 🤖 Compatible with website chat widget

[Learn more about Custom Voices →](https://cookbook.chat-data.com/docs/customize-voices)

## Coming Soon
- Additional voice providers beyond ElevenLabs and Azure
- Custom voice support for real-time voice conversations
`,
};


We’re excited to introduce Customize Voices! Now, your chatbot can respond using your chosen voice when engaging across WhatsApp, Messenger, Instagram, Slack, Discord, and your website chatbot widget.

## What’s New?
- ✅ Personalized Voice Responses – Use a your own custom voice from ElevenLabs in the chatbot' audio replies instead of generic Azure AI voices.
- ✅ Seamless Setup – Just paste your API key from ElevenLabs and select your preferred voice in Chat Data settings.
- ✅ Website Chatbot Support – Enable your customized voice for the embeddable chatbot widget.
- ✅ Third-Party Integration Support – Use your customized voice in responses for WhatsApp, Messenger, Instagram, Slack, and Discord.


For more details, check out the [Customize Voices](https://cookbook.chat-data.com/docs/customize-voices) documentation.

## 🔜 What’s Next?
- More providers: Currently, we support ElevenLabs for custom voice generation and Microsoft Azure for standard voices. If you’d like support for other providers, let us know—we’re open to adding more!
- Customize voice for the realtime voice to voice feature: We're working on extending the customization to the realtime voice to voice feature.

Customize Voices with Your Chatbot

export const article = {
  author: 'Samuel Su',
  date: '2025-03-11',
  title: `Introducing Single Sign-On (SSO) Login`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['sso login', 'chatbot', 'reseller', 'white-labeling', 'chatbot whitelabel'],
  thumbnail: ssoLoginDemo,
  preview:
    `We're excited to launch SSO Login for our Reseller customers, allowing your users to manage their chatbots while maintaining your brand identity throughout.
### 🌟 Key Features

- **Seamless Authentication**: Direct access without Chat Data registration
- **Complete White-Labeling**: Your branding throughout the experience
- **Full Admin Control**: Comprehensive chatbot management and dashboard access
- **Secure & Private**: No user data stored on our platform

### 💪 Capabilities
Users can:
- Manage chatbot settings and behavior
- Access analytics dashboard
- View conversation history
- Configure basic integrations

### 🚀 Quick Setup
1. Configure SSO token generation
2. Add redirect endpoint
3. Test and deploy

For implementation details, check our [documentation](https://cookbook.chat-data.com/docs/setting-up-single-sign-on-sso-redirect).

### 💡 Perfect For
Resellers wanting to provide customers with professional chatbot management capabilities without building custom dashboard solutions.
`,
};


We're excited to announce the launch of SSO Login, a powerful new feature designed specifically for our Reseller customers. This integration enables your customers to manage their chatbots directly in our platform while maintaining your brand identity throughout the experience.


### 🌟 Key Features

- **Seamless Authentication**: Users can access chatbot management directly from our platform without registering with Chat Data.
- **Complete White-Labeling**: Your branding remains consistent throughout the entire user experience
- **Full Admin Access**: Users get comprehensive control over their designated chatbot's settings and dashboard
- **Security First**: No user data is stored on our platform, ensuring your customers' information remains secure

### 💪 What Your Users Can Do
After authentication, users will have full admin access to:
- Customize chatbot settings
- View analytics dashboard
- Manage conversation history
- Configure basic integrations
- Customize AI behavior and responses

### 🔒 Enterprise-Grade Security

- Secure token-based authentication
- Single-session access management
- No storage of user information
- Dedicated white-labeled domain

### 🚀 Getting Started

Setting up SSO Redirect is straightforward:
1. Configure your user management system to generate SSO tokens
2. Add the redirect endpoint to your application
3. Test the integration using our verification tool
4. Deploy to your users

### 📚 Documentation

For detailed implementation instructions and technical specifications, visit this [document](https://cookbook.chat-data.com/docs/setting-up-single-sign-on-sso-redirect).

### 💡 Use Cases

Perfect for:
- Resellers who want to provide their customers with the chatbot settings and dashboard experience while doesn't have the technical support team to build the chatbot settings and dashboard.

Introducing Single Sign-On (SSO) Login

export const article = {
  author: 'Samuel Su',
  date: '2025-03-03',
  title: `Delay Response with Facebook Integrations`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: [    'facebook-integration',
    'whatsapp-bot',
    'messenger-bot',
    'instagram-bot',
    'chatbot-delay',
    'response-time',
    'ai-chatbot',
    'natural-conversation',
    'roleplay-bot',
    'bot-configuration'
  ],
  thumbnail,
  preview:
     `Introducing response delay settings for Facebook integrations. This feature allows you to configure random response delays for your AI chatbots on WhatsApp, Messenger, and Instagram, making interactions feel more natural and less bot-like.

## What's New
- Configure custom delay ranges for each platform
- Random delays between 0-4 hours
- Easy setup through the Integrations tab
- Improved user experience for roleplay scenarios

This update helps create more authentic conversations by preventing instant responses that typically give away AI chatbots.`,
};


## Background
With the WhatsApp, Messenger and Instagram integrations, if the AI chatbot responds immediately after the user's message, it can easily be detected as an AI bot, leading to a poor user experience when using our AI bot for roleplay.

## New Feature
To address this, we've launched a feature to delay the AI agent's response for a configurable amount of time. You can configure the delay time range for each integration. The AI chatbot will randomly delay its response within the range you set, making it harder to detect as an AI bot.

To configure this, simply click the **WhatsApp**, **Messenger** or **Instagram** integration card in the **Integrations** tab.


For example, with the configuration above, the AI chatbot will randomly delay its response uniformly between 0 to 1800 seconds after the response has been generated.

Currently, the average delay time range is between 0 to 2 hours, with the variance range being less than the average time. Therefore, the maximum delay time is less than 4 hours.

Delay Response with Facebook Integrations

export const article = {
  author: 'Samuel Su',
  date: '2025-02-28',
  title: `Duplicate Chatbot`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['duplicate', 'copy', 'chatbot', 'admin', 'configuration'],
  thumbnail,
  preview:
    `Introducing **Chatbot Duplication** - A powerful new feature that enables administrators to clone both chatbot configurations and training data with ease.

## Key Features
- **Full Configuration Copy**: Duplicate your chatbot's entire setup with a single click
- **Optional Training Data**: Choose whether to include or exclude existing training data
- **Secure Transfer**: Sensitive configurations like webhooks and team settings are automatically excluded
- **Flexible Ownership**: New copies are owned by the user initiating the duplication

## Access Control
Available to chatbot owners and users with admin privileges, this feature can be accessed directly from the my-chatbots dashboard.`,
};


We're excited to announce a new feature that allows chatbot administrators to duplicate both configurations and training data when creating a new chatbot. The newly created chatbot will be owned by the user who initiates the copy.





To maintain security and prevent unintended consequences, the following configurations are excluded from the copying process:

- **Operations Settings**

- **Images Assets**

Duplicate Chatbot

export const article = {
  author: 'Samuel Su',
  date: '2025-02-26',
  title: `Claude 3.7 Sonnet Launch`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: [],
  thumbnail,
  preview: `We are excited to announce the launch of [Claude 3.7 Sonnet](https://www.anthropic.com/news/claude-3-7-sonnet) to our chatbot platform. This new model brings significant improvements in speed, accuracy, and thinking capabilities.

## Key Features

### Dual Response Modes
- **Standard Mode**: Delivers near-instant responses without visible thinking process
- **Extended Thinking Mode**: Shows step-by-step reasoning, making the AI's thought process transparent to users

### Performance Improvements
- **Faster Response Generation**: Significantly faster than DeepSeek-R1
- **Better Response Quality**: The new model can generate more accurate response compared with the old Claude 3.5 Sonnet model
- **Enhanced Reasoning Control**: Unlike DeepSeek-R1, Claude 3.7 can effectively disable its thinking output when needed

### Accuracy Enhancements
- **Coding Excellence**: Particularly strong improvements in coding tasks
- **Web Development**: Superior capabilities for front-end web development tasks

## Pricing
Claude 3.7 Sonnet is available at the same price point as Claude 3.5 Sonnet, making it a straightforward upgrade for existing Claude 3.5 Sonnet users.

## Upgrade Recommendation
We recommend all Claude 3.5 Sonnet users upgrade to Claude 3.7 Sonnet to take advantage of these improvements with no additional cost.`,
};


We are excited to announce the launch of [Claude 3.7 Sonnet](https://www.anthropic.com/news/claude-3-7-sonnet) to our chatbot platform. This new model brings significant improvements in speed, accuracy, and thinking capabilities.

## Key Features

### Dual Response Modes
- **Standard Mode**: Delivers near-instant responses without visible thinking process
- **Extended Thinking Mode**: Shows step-by-step reasoning, making the AI's thought process transparent to users

### Performance Improvements
- **Faster Response Generation**: Significantly faster than DeepSeek-R1
- **Better Response Quality**: The new model can generate more accurate response compared with the old Claude 3.5 Sonnet model
- **Enhanced Reasoning Control**: Unlike DeepSeek-R1, Claude 3.7 can effectively disable its thinking output when needed

### Accuracy Enhancements
- **Coding Excellence**: Particularly strong improvements in coding tasks
- **Web Development**: Superior capabilities for front-end web development tasks

## Pricing
Claude 3.7 Sonnet is available at the same price point as Claude 3.5 Sonnet, making it a straightforward upgrade for existing Claude 3.5 Sonnet users.

## Upgrade Recommendation
We recommend all Claude 3.5 Sonnet users upgrade to Claude 3.7 Sonnet to take advantage of these improvements with no additional cost.

Claude 3.7 Sonnet Launch

export const article = {
  author: 'Samuel Su',
  date: '2025-02-24',
  title: `AI Actions in Realtime`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['voice ai', 'ai actions', 'real time voice chat', 'chatbot', 'voice commands', 'pdf generation', 'image generation', 'ai automation'],
  thumbnail,
  preview:
    `Introducing **AI Actions in Realtime** - Extending our AI actions capability to voice conversations, enabling AI agents to perform all actions previously available only in text chat.

## Overview
We've expanded our [AI actions](/changelog/ai-actions) feature to support realtime voice-to-voice interactions. AI agents can now execute actions and display results directly in voice conversations, creating a unified experience across text and voice interfaces.

## New Capabilities
- **Content Generation**: Create images and PDF documents by talking to your AI agent
- **Interactive Features**: Execute searches and trigger button actions via voice
- **Background Processing**: Support for lazy chat actions and lead collection
- **Realtime Results**: View action outcomes directly in the chat interface

## Impact
This update eliminates the previous limitation where AI actions were restricted to text-based interactions, enabling a seamless experience regardless of communication method.
`,
};


Introducing **AI Actions in Realtime** - We've expanded our AI actions capability to support realtime voice-to-voice chat interactions. Your AI agent can now not only answer questions based on your knowledge base but also perform customized AI actions and display results directly in the realtime chat interface.

## Background
Previously, AI actions were only available in text chat mode. Voice-to-voice conversations couldn't utilize features like [lazy live chat](https://cookbook.chat-data.com/docs/live-chat-escalation#lazy-live-chat-triggering), [image and document generation](https://cookbook.chat-data.com/docs/ai-actions#files-and-images-with-api-response), or [custom API calls](https://cookbook.chat-data.com/docs/ai-actions#ai-actions-api). With this update, we've bridged this gap by bringing full AI actions support to the [realtime voice chat](https://cookbook.chat-data.com/docs/realtime-voice-chat).

## Key Features
### Document and Image Generation
Users can now request document or image generation by talking to the AI agent. The AI agent will process these requests using either the [image/document generation API](https://cookbook.chat-data.com/docs/ai-actions#files-and-images-with-api-response) or the [AI PDF action](/changelog/pdf-ai-action), with results displayed directly in the chat interface.


### Search and Button Actions
The AI agent can now execute search queries and button actions during voice conversations, with results seamlessly integrated into the chat interface.


### Background Actions
Background processes like lazy chat actions and lead collection are also supported in voice conversations. While these actions don't display visible results in the interface, they run silently and influence the AI's responses accordingly.

AI Actions in Realtime

export const article = {
  author: 'Samuel Su',
  date: '2025-02-19',
  title: `Customize CSS and Messenger Improvement`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: [],
  thumbnail,
  preview: `We're excited to announce two major updates to enhance your chatbot experience:

## CSS Customization
Fully customize your chat interface's appearance with comprehensive CSS controls. Style everything from containers to buttons through the Settings > Chat Interface panel.

## Messenger Enhancement
Added gender-based personalization support for Facebook Messenger integration, enabling more targeted product recommendations and interactions.

These updates give you more control over your chatbot's appearance and intelligence, helping you create better user experiences.`,
};


## Customize CSS In Chat Interface
You can now customize the CSS of your website's chat interface. We provide extensive customization options for various components including buttons and containers. All available CSS classes are listed below and can be found in the **Settings** > **Chat Interface** tab under the customize CSS section.

### Main Container Elements

### Header Elements

### Message Elements

### Input Elements

### Profile Related Elements

### Navigation & Search Elements

### Multi-Thread Message Elements

### Lead Form Elements

### Chatbot Bubble Elements

### Privacy Consent Elements


To visualize elements with specific CSS classes, you can add a border style in the customize CSS section. For example:

```css
.chat-interface {
  border: 2px solid red;
}
```

## Gender Information In Messenger
The **Messenger** integration now supports gender-based personalization through Facebook profile data. This feature enables your AI chatbot to provide **gender-specific** recommendations for products or services. Currently, this functionality is exclusive to the **Messenger integration** and is not available for **WhatsApp** or **Instagram** integrations.

Customize CSS and Messenger Improvement

export const article = {
  author: 'Samuel Su',
  date: '2025-02-17',
  title: `AI-Powered PDF Document Generation!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['PDF', 'AI', 'Automation', 'Documents', 'Templates'],
  thumbnail,
  preview:
    `
Introducing **AI-Powered PDF Document Generation**! Create and send professional PDFs automatically within conversations.

## 📝 **What's New?**
- ✅ Generate custom PDFs (receipts, agreements, certificates)
- ✅ Auto-extract conversation details into templates
- ✅ Instant A4 PDF delivery

## ⚙️ **How It Works**
- 🔹 Design templates with our rich text editor
- 🔹 Set AI-fillable dynamic fields
- 🔹 Let AI automatically generate personalized PDFs in real-time
`,
};


We're thrilled to introduce **AI-Powered PDF Document Generation**, a game-changing feature that allows you to **automatically create and send professional PDFs** directly within conversations.  

---

## 📝 **What's New?**  
With AI-driven automation, your chatbot can now:  
- ✅ **Generate customizable PDF documents** (e.g., receipts, confirmations, agreements, and certificates).  
- ✅ **Extract relevant details** from conversations and populate predefined templates.  
- ✅ **Deliver professional A4-sized PDFs instantly**—no manual input required.  

---

## ⚙️ **How It Works**  
- 🔹 **Design Your Template** – Use our rich text editor or modify existing templates.  
- 🔹 **Define Variables** – Set fields with descriptions for AI to fill dynamically.  
- 🔹 **Preview & Generate** – Click "Generate PDF" to instantly create a formatted document.  
- 🔹 **Seamless AI Execution** – The chatbot gathers user details and **automatically** generates a personalized PDF in real time.

AI-Powered PDF Document Generation!

export const article = {
  author: 'Samuel Su',
  date: '2025-02-14',
  title: `New AI Models & Enhanced Reasoning Interface`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['models','deepseek', 'openai', 'gemini'],
  thumbnail,
  preview:
    `
Introducing powerful AI model upgrades to enhance your chatbot capabilities:

## 🧠 New AI Models
- GPT O1 – Advanced reasoning for STEM & coding
- GPT O3 Mini – Fast, efficient technical processing
- Deepseek R1 – High-performance reasoning
- Gemini 2.0 Flash – Low-latency multimodal support

## 🤖 New Features
- Real-time reasoning interface with step-by-step visibility
- Enhanced model selection including Gemini Flash 2.0 & Gemini 2.0 Pro
- Seamless tool integration and workflow optimization
`,
};


We're excited to introduce **powerful new AI upgrades** to enhance your chatbot's capabilities and streamline workflows.  

## 🧠 **New AI Models Available**  
- 🔹 **GPT O1** – Advanced deep reasoning model for complex STEM and coding tasks, leveraging chain-of-thought processing.  
- 🔹 **GPT O3 Mini** – Fast and cost-efficient, optimized for technical tasks with seamless tool call support.  
- 🔹 **Deepseek R1** – High-efficiency reasoning model delivering strong performance with minimal resource use.  
- 🔹 **Gemini 2.0 Flash (Experimental)** – Google's low-latency multimodal model for rapid tool integration and agentic workflows.  

## 🤖 **Enhanced Reasoning Interface**  
Since **Deepseek R1** and **Claude 3.0 Opus** support reasoning outputs via API, we've integrated a **real-time reasoning interface** into your chatbot.   
- ✅ Enabled by default for these models.  
- ✅ View the model's step-by-step thought process in real time.  
- ✅ Easily toggle this feature on or off as needed.  

## 🌟 **More Model Options**  
We've also added **Gemini Flash 2.0 (Production)** and **Gemini 2.0 Pro (Experimental)**, giving you even more flexibility to optimize your chatbot for various workflows.

New AI Models & Enhanced Reasoning Interface

export const article = {
  author: 'Samuel Su',
  date: '2025-02-05',
  title: `Stripe Metering Integration`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['stripe', 'billing', 'metering', 'usage-based', 'integration'],
  thumbnail,
  preview:
    `
Introducing **Stripe Metering Setup** for seamless usage-based billing of your chatbots.

## 🚀 **Quick Setup**

1️. Connect Stripe account in **Account Settings**  
2. Create meter and pricing model in Stripe  
3. Enable metering in **Settings > Metering**  

## ⚙️ **Features**  
- Bill by message credits or count  
- Support for static (fixed) or dynamic (lead-based) customers  
- Track usage via email, name, or phone  

Monitor real-time usage in Stripe's Metering Dashboard.
`,
};



We're excited to introduce **Stripe Metering Setup**, allowing you to **track and charge for chatbot usage seamlessly** with Stripe's usage-based billing.  

## 🚀 **How It Works**  
1️. **Add Your Stripe API Key** – Connect your Stripe account in **Chat Data > Account Settings**.  
2.  **Set Up a Meter in Stripe** – Follow Stripe's guide to create a **meter and pricing model**.  
3. **Enable Metering for Your Chatbot** – Configure usage tracking in **Chat Data > Settings > Metering**.  

## ⚙️ **Key Metering Options**  
- 🔹 **Metering Type** – Charge users based on **message credits** or **raw message count**.  
- 🔹 **Static vs. Dynamic Customers** –  
&nbsp;&nbsp;&nbsp;✔ **Static:** Charge a fixed customer (e.g., a reseller).  
&nbsp;&nbsp;&nbsp;✔ **Dynamic:** Charge based on lead information (email, phone, or name).  
- 🔹 **Customer Identification** – Identify users by **email (recommended), name, or phone** for accurate billing.  


## ✅ **Verify Your Setup**  
After configuration, chat with your chatbot and check **Stripe's Metering Dashboard** to see real-time usage tracking.

Stripe Metering Integration

export const article = {
  author: 'Samuel Su',
  date: '2025-02-02',
  title: `Multithread Conversations`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['ai', 'mutli-threads', 'website chatbot', 'customer support'],
  thumbnail,
  preview:
    `
Introducing **Multithread Conversations**: Switch seamlessly between multiple chat threads while maintaining context. With real-time notifications and powerful search capabilities, managing parallel conversations has never been more efficient.

## 🔥 **What's New?**  
- ✅ Manage multiple conversations simultaneously  
- ✅ Real-time response notifications  
- ✅ Quick conversation search  
`,
};


We're excited to introduce **Multithread Conversations**, a powerful upgrade that makes managing multiple conversations effortless! Now, you can switch between chat threads **without losing context**, improving multitasking and efficiency.  

---

## 🔥 **What's New?**  
- ✅ **Effortlessly manage multiple conversations** in a single interface.  
- ✅ **Real-time notifications** when a human agent responds.  
- ✅ **Keyword-based search** to quickly access past conversations.  

---

## 💡 **Why It Matters**  
Whether you're handling multiple customer inquiries, tracking ongoing discussions, or collaborating with your team, **Multithread Conversations** ensures smooth, uninterrupted interactions.

Multithread Conversations

export const article = {
  author: 'Samuel Su',
  date: '2025-01-24',
  title: `Chatbot Time Awareness!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['AI', 'Chatbot', 'Time-Awareness', 'Customer Service', 'Automation'],
  thumbnail,
  preview: `
Introducing **Chatbot Time Awareness** - Now your AI chatbot can recognize the current time and respond intelligently! 

## ⏰ What's New?
- ✅ Detect user's local time or set custom time zones
- ✅ Dynamic time-based responses
- ✅ Smart handling of business hours and promotions

Set up time-based rules like _"Notify customers when store is closed"_ or _"Promote morning specials"_ to deliver perfectly timed, automated responses that enhance customer experience.
`,
};


We're excited to introduce **Chatbot Time Awareness**, a powerful new feature that allows your AI chatbot to recognize the **current time** and adjust its responses accordingly!  

---

## ⏰ **What's New?**  
Your chatbot can now:  
- ✅ **Detect the user's local time** (via browser settings) or a **designated time zone**.  
- ✅ **Respond dynamically** based on the time of day.  
- ✅ **Handle time-sensitive inquiries** like store hours, promotions, or service availability.  

---

## 🛠 **How It Works**  
Enable **Time Awareness** and set up time-based prompts such as:  

🕕 _"If it's after 6:00 PM, let customers know that our store is closed."_  
🎉 _"If it's between 9:00 AM - 12:00 PM, promote our morning special discount!"_  

This feature ensures your chatbot **delivers accurate, time-relevant responses**—enhancing customer experience and automating business communications.

Chatbot Time Awareness!

export const article = {
  author: 'Samuel Su',
  date: '2025-01-15',
  title: `Customizable Lead Form Builder!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['lead-form-builder', 'lead-collection', 'custom-fields',  'chatbot-lead-collection', 'CRM'],
  thumbnail,
  preview:
    `
Introducing our **Customizable Lead Form Builder** to capture the exact information your business needs.

## 🎯 **Key Features**
- ✅ **Flexible Fields** – Add custom text fields, checkboxes, and dropdowns
- ✅ **Better Lead Quality** – Collect industry-specific details beyond basic contact info
- ✅ **Smart Integration** – All custom fields are searchable and included in daily summaries

`,
};


We’re excited to launch a powerful new feature that lets you **tailor your lead forms** to collect the exact information your business needs.  

## 🎯 **Why This Matters**  
Different industries require different lead details—basic fields like **Name, Email, and Phone** aren't always enough. With our **Customizable Lead Form Builder**, you can now:  

- ✅ **Add Custom Fields** – Include **single-line text, multi-line text areas, checkboxes, and dropdowns** to capture the right information.  
- ✅ **Improve Lead Quality** – Gather industry-specific details like company size, current software providers, or any data relevant to your business.  
- ✅ **Enhanced Search & Tracking** – All custom fields are **indexed and searchable** in your chat logs and **included in daily lead summary emails**.

Customizable Lead Form Builder!

export const article = {
  author: 'Samuel Su',
  date: '2025-01-15',
  title: `IP Blocklist & Allowlist`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['Security', 'IP Blocking', 'Access Control', 'Chatbot Security', 'Geo Blocking', 'Spam Prevention'],
  thumbnail,
  preview:
    `
Introducing **IP-based access control** with customizable blocklists and allowlists for enhanced chatbot security.

## 🚀 **Features**  
- ✅ Block unwanted users and prevent spam
- ✅ Control access by country or region
- ✅ Restrict usage to authorized IP ranges

## ⚙️ **How It Works**  
- **Blocklist** – Denied IPs can't access the chatbot
- **Allowlist** – Optional whitelist for authorized IPs
- **Priority** – Blocklist takes precedence over allowlist

## 🔧 **Setup**  
Configure in **Settings > Security** or manage directly from dashboards 

`,
};


We’re excited to introduce **IP-based access control** for your chatbot! Now, you can **enhance security and manage user access** with customizable **blocklists** and **allowlists**.  

## 🚀 **What You Can Do**  
- ✅ **Block malicious users** and prevent spam  
- ✅ **Restrict access by country** to comply with regulations or business needs  
- ✅ **Limit chatbot usage** to specific company networks or authorized IPs  

## ⚙️ **How It Works**  
- 🔹 **Blocklist Check** – If an IP is in the blocklist, access is denied. Otherwise, it moves to the allowlist check.  
- 🔹 **Allowlist Check** – If the allowlist is empty, all users (except blocked ones) can access the chatbot. If the allowlist has entries, only listed users are allowed.  
- 🔹 **Full Access Control** – Even if an IP is in the allowlist, it will be blocked if also found in the blocklist.  

## 🔧 **How to Set It Up**  
Go to **Settings > Security** to configure your blocklist and allowlist. You can also block/unblock IPs directly from the **Chat Logs, Leads Dashboard, and Live Chat Dashboard**.  


Check out the [IP Blocklist & Allowlist](https://cookbook.chat-data.com/docs/ip-blocklist-and-allowlist-security) documentation for more details.

IP Blocklist & Allowlist

export const article = {
  author: 'Samuel Su',
  date: '2024-12-20',
  title: `AI Actions – Your Chatbot, Now an AI-Agent!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['AI-Agents', 'Automation', 'ChatBot', 'Integration', 'LeadGen'],
  thumbnail,
  preview:
    `
Introducing **AI Actions** - Transform your chatbot into a powerful AI agent that can perform real-world tasks! 

## ⚡ Key Features
- **Lead Generation** - Capture and qualify leads automatically
- **Custom Actions** - Trigger buttons, forms, and external links
- **Smart Integration** - Real-time web search and API connectivity
- **Rich Media** - Send images, PDFs, and documents on demand

## 🔥 Available Platforms
Seamlessly integrate with Web Widgets, WhatsApp, Messenger, Instagram, Discord, and Slack to automate your business workflows.

Check the [AI Actions](https://cookbook.chat-data.com/docs/ai-actions) page for more details.
`,
};


We're excited to introduce **AI Actions**, a game-changing feature that transforms your chatbot into a powerful AI agent, capable of performing real-world tasks on your behalf!  

---

## ⚡ **What Can AI Actions Do?**  
With **AI Actions**, your bot moves beyond simple Q&A and takes on **sales and support tasks** to **drive business outcomes**. Here's what's possible:  

- ✅ **Trigger Lead Forms** – Dynamically capture and qualify leads based on user queries.  
- ✅ **Activate Custom Buttons** – Seamlessly redirect users to booking pages, order forms, or external links.  
- ✅ **Smart Web Search** – Your chatbot **knows when** to search the web and fetch real-time data.  
- ✅ **AI Actions API** – Integrate your own API endpoints, enabling the bot to interact with your business systems in real time.  
- ✅ **Send Images & PDFs** – Deliver images, receipts, and documents in response to user requests.  

---

## 🔥 **AI Actions in Action**  
These features work **seamlessly across all major platforms**:  

🌍 **Web Widget Integration** – AI-powered interactions embedded in your website.  
📱 **WhatsApp Integration** – Automate responses and send documents.  
📩 **Messenger & Instagram** – Handle inquiries, book appointments, and more.  
💬 **Discord & Slack** – Enable intelligent bot interactions for teams and communities.  

---

Check the [AI Actions](https://cookbook.chat-data.com/docs/ai-actions) page for more details.

AI Actions – Your Chatbot, Now an AI-Agent!

export const article = {
  author: 'Samuel Su',
  date: '2024-11-17',
  title: `New AI Models Now Available!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['AI', 'Claude', 'Gemini', 'ChatBot', 'LLM models'],
  thumbnail,
  preview:
    `
We're excited to announce **six powerful AI models** for enhanced chatbot capabilities.
## 🧠 **New AI Models**  
- 🔹 **Claude 3.5 Sonnet** – Anthropic's advanced model for complex reasoning
- 🔹 **Claude 3.5 Haiku** – Fast, lightweight model for efficient conversations
- 🔹 **Claude 3 Haiku** – Streamlined model for quick, intelligent responses
- 🔹 **Claude 3 Opus** – Anthropic's most powerful AI for deep reasoning
- 🔹 **Gemini 1.5 Flash** – Google's rapid multimodal model for tool integration
- 🔹 **Gemini 1.5 Pro** – An advanced model that provides higher intelligence and capability

## 🚀 **Benefits**  
- ✅ **Flexible Options** – Choose models based on speed vs. reasoning needs
- ✅ **Better Performance** – Improved efficiency and response times
- ✅ **Easy Integration** – Optimize for cost, speed, and intelligence
`,
};


We’re excited to announce the launch of **six powerful AI models** to give you more flexibility, speed, and efficiency in your chatbot workflows.  

## 🧠 **Introducing the Latest AI Models**  
- 🔹 **Claude 3.5 Sonnet** – Anthropic’s most advanced model, offering enhanced reasoning and speed for complex tasks.  
- 🔹 **Claude 3.5 Haiku** – A fast, lightweight model optimized for real-time conversations with high efficiency.  
- 🔹 **Claude 3 Haiku** – A streamlined version of Claude 3, built for quick responses with strong language understanding.  
- 🔹 **Claude 3 Opus** – Anthropic’s most powerful AI, designed for deep reasoning and detailed, structured responses.  
- 🔹 **Gemini 1.5 Flash** – Google’s high-speed multimodal model for rapid tool integrations and dynamic interactions.  
- 🔹 **Gemini 1.5 Pro** – An advanced model that provides higher intelligence and capability compared to Gemini 1.5 Flash by Google..  

## 🚀 **Why It Matters**  
- ✅ **More choices** – Pick the best model based on your needs, whether it’s advanced reasoning or high-speed conversations.  
- ✅ **Enhanced AI performance** – Improved efficiency, accuracy, and response times across all chatbot interactions.  
- ✅ **Seamless integration** – Easily switch between models to optimize cost, speed, and intelligence.

New AI Models Now Available!

export const article = {
  author: 'Samuel Su',
  date: '2024-10-27',
  title: `Enhanced Metrics & Reporting`,
  tagLink: 'insights',
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['analytics', 'reporting', 'metrics', 'dashboard', 'chatbot'],
  thumbnail,
  preview:
    `
We've expanded your **dashboard analytics** with powerful new insights and reporting tools! Now, you can track chatbot performance more effectively than ever.

## What's New:
- ✅ **Enhanced Dashboard Metrics** – Track messages, conversations, satisfaction scores, leads, and topic categories  
- ✅ **Topics Categorization** – Pre-curated categories to understand user intent  
- ✅ **Public Metrics Page** – Share and embed white-labeled performance metrics  
- ✅ **Automated Reports** – Get weekly and monthly performance summaries in your inbox

Navigate to **Settings > Analytics** to customize your metrics and reporting preferences.
`,
};


We've expanded your **dashboard analytics** with powerful new insights and reporting tools! Now, you can track chatbot performance more effectively than ever.

## 📈 **New Dashboard Metrics**  
Your analytics dashboard now includes **five new key metrics**:  
- ✅ **Total Messages** – Track all interactions over time.  
- ✅ **Total Conversations** – Measure unique chatbot sessions.  
- ✅ **Upvotes & Downvotes** – Gauge user satisfaction.  
- ✅ **Submitted Leads** – Monitor lead generation performance.  
- ✅ **Categorized Topics** – See what users are talking about.  

These insights are displayed in **timeline graphs for trends** and **pie charts for clear segmentation**.  

## 🏷️ **Topics Categorization**  
Understanding user intent just got easier! 🚀  
- We've pre-curated **50 industry-specific topics** to help categorize user messages.  
- **Fully customizable**: Adjust categories to **match your chatbot's focus**.  
- Navigate to **Settings > Analytics** to refine your topic categories.  

## 🌐 **Public Metrics Page**  
For resellers and businesses looking to **showcase chatbot value**, we've introduced a **white-labeled metrics page**:  
🔗 **Share chatbot performance** via a public link.  
🌍 **Embed metrics** on your website using an iframe.  
🎛 **Control visibility**: Choose which metrics to display.  

📌 **Try It Out!** Explore an example white-labeled link to see it in action.  

## 📅 **Automated Weekly & Monthly Summaries**  
Stay updated with **scheduled performance reports** straight to your inbox!  
📌 **Weekly Summary** – Key chatbot stats from the past 7 days.  
📌 **Monthly Summary** – A comprehensive report on last month's performance.  

📨 **Enable summaries in** **Settings > Notifications** and even test the email functionality instantly!  

## 🎉 **Get Started Today!**  

Check the [Analysis Dashboard](https://cookbook.chat-data.com/docs/usage-data-dashboard#analysis-dashboard) page for more details.

Enhanced Metrics & Reporting

export const article = {
  author: 'Samuel Su',
  date: '2024-10-20',
  title: `Introducing Realtime Voice Chat`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['voice-chat', 'realtime-ai', 'chatbot', 'voice-recognition', 'lead-generation'],
  thumbnail,
  preview:
    `
Introducing **Realtime Voice Chat** - engage with your chatbot through natural voice conversations! This groundbreaking feature enables fluid, human-like interactions while automatically collecting lead information.

🔑 **Key Features:**
- Natural voice conversations with customizable AI voices
- Automatic lead information extraction (name, email, phone)
- Multi-language support
- Adjustable voice detection parameters
- Chat log audio playback

💰 **Cost-Efficient:**
- Available on Standard and above plans
- Flexible RAG settings to optimize costs
- Choose between high-quality (gpt-4-realtime) and cost-effective (gpt-4-realtime-min) models

🎯 **Perfect for:**
- Customer service automation
- Lead generation
- Sales qualification
- Support desk enhancement

Enable Realtime Voice Chat today and transform your chatbot into a dynamic conversational agent!
`,
};


We're excited to roll out **Realtime Voice Chat**, a groundbreaking feature that lets your chatbot communicate **just like a real person**! With this update, users can engage in **natural voice conversations**, making interactions **faster, more engaging, and more intuitive**.  

🚀 **Available on Standard and Above Plans**  

---

## 🔧 **How to Enable Realtime Voice Chat**  
Realtime Voice Chat is **not enabled by default** due to its **high resource costs**. To activate it:  
1️⃣ Go to **Settings** > **Realtime Audio**.  
2️⃣ Choose the **voice avatar** that appears in the chatbot.  
3️⃣ Set a **default voice** (users can change this later).  
4️⃣ Preview available voices before selecting.  

---

## 🎙️ **Realtime Voice Chat Features**  

### - ✅ **Audio Playback in Chat Logs**  
- By default, **original voice interactions** are stored and available in the **Chat Logs Dashboard** for review.  
- Disabling this option will store only **text transcripts** (generated by OpenAI's Whisper model).  

### ⚙️ **Adjustable Voice Chat Parameters**  
Fine-tune voice interaction settings for a seamless experience:  
- **Threshold** – Adjust voice activity detection sensitivity.  
- **Prefix Padding** – Set how much audio before speech recognition is included.  
- **Silence Duration** – Define when the chatbot considers speech to have ended.  
- **RAG Limit** – Control how much context is retrieved per message to **optimize costs**.  

Users can also **change voices dynamically** via the voice selection overlay. 🌍 **Multi-language support** is available!  

---

## 💰 **Cost & Pricing**  
Voice-based interactions are processed through **OpenAI's realtime API**, which is more resource-intensive than text-based queries.  

📌 **Cost Optimization Tip:**  
- By default, the chatbot retrieves **10 RAG text chunks** (~3,000 tokens). Lowering this to **5 chunks** reduces costs.  
- **gpt-4-realtime-min-preview** is **more cost-effective** than gpt-4o-mini, averaging **1 credit per message**.  
- Messages **without context retrieval** cost ~10 credits, while those **with context retrieval** cost **30-40 credits**.  

📊 **View Credit Usage:**  
You can check **cost per message** in the **Chat Logs dashboard** by hovering over the **question mark icon**.  

---

## 📇 **Lead Information Collection**  
With **Realtime Voice Chat**, lead collection is fully automated! 🎯  
- The chatbot can **extract and store** user details like **name, phone number, and email** directly from conversations.  
- This data is synced to **your leads dashboard, webhooks, and CRM**.  
- The chatbot **remembers lead information** for future conversations, even after a page refresh.  

💡 **Customize Data Collection:**  
Modify the chatbot's **base prompt** to gather user details **before providing further service**.  

---

## 🎉 **Get Started Today!**  
1️⃣ Enable **Realtime Voice Chat** from the **Settings page**.  
2️⃣ Fine-tune parameters for **cost efficiency and accuracy**.  
3️⃣ Enjoy **natural voice conversations** with **automated lead capture**!  

🚀 Experience a **truly conversational AI** with **Realtime Voice Chat** today!  

Check the [Realtime Voice Chat](https://cookbook.chat-data.com/docs/realtime-voice-chat) page for more details.

Introducing Realtime Voice Chat

export const article = {
  author: 'Samuel Su',
  date: '2024-10-11',
  title: `Enhanced Scraping & Automated Website Retraining`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['webscraping', 'automation', 'training', 'captcha', 'updates'],
  thumbnail,
  preview:
    `
Introducing Enhanced Scraping and Automated Website Retraining to improve chatbot training efficiency and accuracy.

## 🚀 Enhanced Scraping Features

- **Authenticated Pages Access**
  - Train on both public and login-protected pages

- **CAPTCHA Handling**
  - Automatic Cloudflare CAPTCHA bypass

- **Smart Content Filtering**
  - Removes headers, footers, and pop-ups
  - Up to 5x more pages within training limits

## 🔄 Automated Retraining

- **Scheduling Options**
  - Entry Plan: Monthly updates
  - Standard Plan+: Weekly/daily updates

- **Flexible Configuration**
  - List Mode: Preserve structure
  - Auto/Sitemap Mode: Remove outdated content
  - Page Options: Filter irrelevant content

Note: Scrape credits required per URL processed.

## Quick Setup
1. Enable authenticated page scraping
2. Configure cron job schedule
3. Set page filtering options
`,
};


We're excited to introduce **Enhanced Scraping Options** and **Automated Website Retraining**, making chatbot training more efficient, accurate, and adaptable to dynamic website content.  

## 🚀 **Enhanced Scraping Options**  

We've addressed key scraping challenges to give you **greater control and accuracy** when training your chatbot:  

- **Access to Authenticated Pages**  
  - Train your chatbot on both public and **authenticated** web pages requiring login credentials.  

- **Cloudflare CAPTCHA Solver**  
  - Our new scraper **bypasses Cloudflare CAPTCHAs with 100% accuracy**, ensuring uninterrupted website scraping.  

- **Improved Content Filtering**  
  - Websites often contain irrelevant elements like headers, footers, and cookie pop-ups that clutter training data.  
  - Our enhanced scraper now **filters out non-essential elements**, significantly increasing the number of pages within your training limit.  
  - Example: One user expanded their chatbot's training set from **600 to 3,500 pages** by removing redundant content—without losing critical information.  

These upgrades ensure your chatbot can **train more effectively on both public and authenticated pages**, delivering **refined and high-quality responses**.  
📖 **Check the Page Options in our cookbook** for detailed configuration steps.  

---

## 🔄 **Automated Website Retraining**  

Keep your chatbot's knowledge base **up to date—automatically!**  

### How It Works  
Once your chatbot is trained on website URLs, you can set up a **cron job** to periodically fetch new content and retrain the chatbot.  

- **Entry Plan:** Monthly retraining  
- **Standard Plan & Above:** Weekly or daily retraining  

### Customization Options  
- **Choose Your Crawl Type:**  
  - **List Mode**: Keeps the existing structure intact.  
  - **Automatic Mode** & **Sitemap Mode**: Identify and remove outdated pages.  
- **Apply Page Options:**  
  - Extract only **relevant content** to improve training quality.  

### Scrape Credit Usage  
To maintain efficiency for all users, **each scraped page URL will consume scrape credits**.  

---

## - ✅ **Get Started Today**  
1️⃣ Enable **scraping for authenticated pages** in your chatbot settings.  
2️⃣ Set up a **cron job** to automate website retraining.  
3️⃣ Optimize training by configuring **Page Options** for cleaner, more focused content extraction.  

Check the [Page Options](https://cookbook.chat-data.com/docs/train-with-your-data#page-options) and [Automated Website Retraining](https://cookbook.chat-data.com/docs/train-with-your-data#automated-website-retraining) page for more details.
---

Enhanced Scraping & Automated Website Retraining

export const article = {
  author: 'Samuel Su',
  date: '2024-10-04',
  title: `Multi-modal Inputs`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['multi-modal', 'inputs', 'chatbot', 'ai', 'customerservice'],
  thumbnail,
  preview:
    `
Introducing Multi-modal Inputs: Upload files and images during chat interactions for enhanced AI responses based on your training data.

## Key Features

- **File & Image Support**
  - Available in Standard plan and above
  - Enable in Settings > Chat Interface
  - Real-time file/image uploads during chats

- **RAG Processing**
  - Files: Extracts and analyzes content against knowledge base
  - Images: Performs text extraction and context matching
  - Customizable image analysis prompts

- **Live Chat Integration**
  - File/image sharing between customers and agents
  - Email notifications for offline sharing

## Setup
1. Upgrade to Standard plan or higher
2. Enable in Settings > Chat Interface
3. Configure prompts and test with the Sparkles icon
`,
};


We're thrilled to announce the launch of Multi-modal Inputs—a powerful new feature that enhances your chatbot's capabilities by enabling file and image uploads during interactions. Now, your chatbot can analyze documents and images to provide insightful, contextually accurate responses based on your training data and base prompts.

## What's New

- **File & Image Uploads:**  
  - Activate Multi-modal Inputs in **Settings > Chat Interface** (available in Standard plan and above).
  - Upload files and images directly during chat interactions.

- **Enhanced AI Chat:**  
  - The chatbot now demonstrates its analytical prowess by examining uploaded documents and images, delivering precise responses to your queries.

- **Files RAG (Retrieval Augmented Generation):**  
  - Uploaded files are processed by extracting and analyzing content to find relevant matches in your knowledge base, ensuring accurate and contextual chatbot responses.

- **Images RAG:**  
  - **Two-step Image Processing:**
    1. **Text Extraction:** Extracts text content from uploaded images.
    2. **Context Matching:** Matches the extracted text against your knowledge base.
  - **Customizable Prompts:**  
    Tailor the text extraction prompt to capture only the relevant details. For example, if your store specializes in specific products, you can use a custom prompt:
    ```
    Create concise descriptions of products in the image, including product type, text, etc. Be very concise and straight to the point. Possible product types are:
    - magnet
    - ayna
    - baskili-kese
    - mert-sunnet-davetiye
    - greeting card
    ```
  - Test your custom prompt by clicking the Sparkles icon and uploading an image to view the extracted text.

- **Live Chat Enhancements:**  
  - Seamlessly exchange files and images between customers and live agents during chat sessions.
  - If either party is offline, the system automatically sends an email notification with the shared files and images to ensure uninterrupted communication.

## Get Started

1. **Upgrade:** Ensure you're on the Standard plan or above.
2. **Activate:** Navigate to **Settings > Chat Interface** to enable Multi-modal Inputs.
3. **Customize & Test:** Adjust your base prompts as needed, and test image uploads using the Sparkles icon.

Check the [Multi-modal Inputs](https://cookbook.chat-data.com/docs/multi-modal-inputs) page for more details.

Multi-modal Inputs

export const article = {
  author: 'Samuel Su',
  date: '2024-10-01',
  title: `Bidirectional Website & Chatbot Communication`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['postMessage', 'integration', 'personalization', 'authentication', 'events'],
  thumbnail,
  preview:
    `
Introducing bidirectional communication between your website and AI chatbot for personalized user experiences.

## 🔄 Key Features

### **📡 Website to Chatbot**
- Send authenticated user data via postMessage API
- Enable personalized chatbot responses
- Access user-specific metrics for targeted interactions

**🚀 Demo:** Try asking **What is my name?** or **Double my lucky number** on our [Demo Website](https://openai-assistant-demo.chat-data.com/)

### **📩 Chatbot to Website**
Listen for events from the chatbot widget:
- Chat interactions
- Live chat escalation
- Widget state changes
- Lead form submissions

Your website can respond dynamically to these events with personalized UI updates and pop-ups.

## - ✅ Quick Setup
1. Implement postMessage API for user data
2. Add event listeners for chatbot interactions
3. Test on our [Demo Website](https://openai-assistant-demo.chat-data.com/)
`,
};


We're excited to introduce a powerful new feature that enables **seamless two-way data exchange** between your website and AI chatbot. This update allows your chatbot to provide **personalized interactions** based on user information, creating a **more engaging and tailored experience** for every visitor.  

---

## 🔄 **How It Works**  

### **📡 Send User Information from Website to Chatbot**  
- If your website uses **user authentication**, you can now transmit user details to the chatbot via the **postMessage API**.  
- This eliminates redundant data collection and enhances personalization.  
- Example: If your website provides **diagnostic tools**, the chatbot can access user-specific metrics to answer follow-up queries.  

**🚀 Try it Live:** Visit our **[Demo Website](https://openai-assistant-demo.chat-data.com/)** to see this feature in action!  
- Enter your user information.  
- The chatbot will recognize details like your **lucky number** and respond accordingly.  
- Ask **"What is my name?"** or **"Double my lucky number"** to see real-time personalization in effect.  

This demonstrates how syncing user data **enhances chatbot interactions** and creates a customized user experience.  

---

### **📩 Receive PostMessage Events from Chatbot to Website**  
When embedding our chatbot as a **widget bubble or iframe**, your website can now listen for these chatbot events:  
- ✅ **Chat events** – Track user interactions.  
- ✅ **Live chat escalation** – Detect when a user requests human support.  
- ✅ **Minimize widget** – Monitor when the chatbot is hidden.  
- ✅ **Lead submission** – Capture user contact details.  

**🚀 Try it Live:** Visit our **[Demo Website](https://openai-assistant-demo.chat-data.com/)** to see real-time postMessage events in action!  
- Click **"Clear Lead Info"** to reset.  
- Start a conversation with the chatbot.  
- When submitting a lead form, the website will **instantly display** the captured user details.  

This feature enables **real-time website responses** based on chatbot interactions, allowing you to:  
✨ Display **personalized pop-ups** featuring the user's name and email.  

Check the [PostMessage Events](https://cookbook.chat-data.com/docs/postmessage-events) page for more details.

Bidirectional Website & Chatbot Communication

export const article = {
  author: 'Samuel Su',
  date: '2024-09-25',
  title: `Introducing Zapier/Make Integration`,
  tagLink: 'insights',
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['Zapier', 'Make', 'Integration', 'Automation', 'CRM', 'API', 'Chatbot'],
  thumbnail,
  preview:
    `
We're excited to announce a powerful new addition to Chat Data: a Zapier/Make integration that bridges the gap between our native chatbot capabilities and your favorite apps. This integration empowers your chatbot to act as your personal AI agent—helping you draft emails, create CRM tickets, and automate workflows.

## What's New:
- **Extended App Connectivity:**  
  Connect to Gmail, HubSpot, WhatsApp, and more through our Zapier/Make integration bridge.

- **Triggering Events:**  
  - **Lead Submission:** Activates when a new lead is submitted.  
  - **Live Chat Escalation:** Fires when a live chat escalation is requested.  
  - **New Message:** Triggers when a new message is received.

- **New API Actions:**  
  Create chatbots, send messages, and update base prompts with our new API endpoints.

Get started quickly with 15 pre-built templates for lead tracking, email follow-ups, and live chat monitoring. Retrieve your API key from account settings to begin automating today!
`,
};


We're excited to announce a powerful new addition to Chat Data: a Zapier/Make integration that bridges the gap between our native chatbot capabilities and the multitude of apps you love. This integration empowers your chatbot to act as your personal AI agent—helping you draft emails, create CRM tickets, respond to messages, and much more.

## What’s New:
- **Extended App Connectivity:**  
  While our native integrations cover a select few major apps, the Zapier/Make integration lets you connect to many more services—including Gmail, HubSpot, WhatsApp, and SMS gateways—by serving as the automation bridge.

- **Triggering Events (Available on Standard & Professional Plans):**  
  - **Lead Submission:** Activates when a new lead is submitted.  
  - **Live Chat Escalation:** Fires when a live chat escalation is requested.  
  - **New Message:** Triggers when a new message is received.

- **New API Actions:**  
  - **Create a Chatbot:** Easily spin up a new chatbot if you're under your allocation limit.  
  - **Send a Message:** Interact with your chatbot and receive a response in real time.  
  - **Update Base Prompt:** Modify the chatbot’s base prompt to tailor its behavior to your needs.

- **Easy Setup with Integration Portal:**  
  Manage your Zapier integration flows directly within the Integration tab. Plus, get started quickly with 15 pre-built templates designed for various use cases—from lead tracking and email follow-ups to live chat monitoring and more.

## Use Cases at a Glance:
- **Monitor and Act on Chat Messages:**  
  Automatically store, analyze, and respond to user messages.
- **Seamless CRM Integration:**  
  Record new leads in your CRM (e.g., HubSpot, Zendesk) or trigger follow-up emails via SendGrid or Gmail.
- **Efficient Escalation Handling:**  
  Redirect live chat escalation requests to your team through SMS, email, or ticketing systems.
- **Daily Digest Automation:**  
  Turn daily Gmail digests into actionable to-do lists using a temporary base prompt.
- **Cross-Platform Messaging:**  
  Respond to messages on Slack or SimpleTexting, ensuring you never miss a beat.

Check the [Zapier Integration](https://cookbook.chat-data.com/docs/zapier-integration) and [Make Integration](https://cookbook.chat-data.com/docs/make-integration) page for more details.

Introducing Zapier/Make Integration

export const article = {
  author: 'Samuel Su',
  date: '2024-09-17',
  title: `Seamless Live Chat Takeover for WhatsApp, Messenger, and Instagram!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['WhatsApp', 'Messenger', 'Instagram', 'LiveChat', 'CustomerSupport', 'AI'],
  thumbnail,
  preview:
    `
We’re excited to announce a major upgrade to our live chat experience—**human agents can now seamlessly take over conversations from the AI** across **WhatsApp, Messenger, and Instagram**!  

### 🔥 **What’s New?**  
Previously, WhatsApp’s AI integration restricted live interactions once a phone number was connected. Now, with this update, you can personally step in and handle complex customer queries across all three platforms!  

### 💡 **How It Works:**  
- ✅ **Live Chat Control** – Select any conversation thread in the Live Chat dashboard.  
- ✅ **AI Toggle** – Disable the AI chatbot while engaging with the customer to prevent interruptions.  
- ✅ **Direct Messaging** – Your responses will be delivered straight to the customer’s app (WhatsApp, Messenger, or Instagram).  
- ✅ **Offline Notifications** – If the AI is disabled and you’re offline, you’ll receive an email alert with a chat link whenever a customer replies.  

This update ensures a **seamless handoff between AI automation and human support**, giving your customers the **best of both worlds!** 🎉  
`,
};


We’re excited to announce a major upgrade to our live chat experience—**human agents can now seamlessly take over conversations from the AI** across **WhatsApp, Messenger, and Instagram**!  

### 🔥 **What’s New?**  
Previously, WhatsApp’s AI integration restricted live interactions once a phone number was connected. Now, with this update, you can personally step in and handle complex customer queries across all three platforms!  

### 💡 **How It Works:**  
- ✅ **Live Chat Control** – Select any conversation thread in the Live Chat dashboard.  
- ✅ **AI Toggle** – Disable the AI chatbot while engaging with the customer to prevent interruptions.  
- ✅ **Direct Messaging** – Your responses will be delivered straight to the customer’s app (WhatsApp, Messenger, or Instagram).  
- ✅ **Offline Notifications** – If the AI is disabled and you’re offline, you’ll receive an email alert with a chat link whenever a customer replies.  

This update ensures a **seamless handoff between AI automation and human support**, giving your customers the **best of both worlds!** 🎉

Seamless Live Chat Takeover for WhatsApp, Messenger, and Instagram!

export const article = {
  author: 'Samuel Su',
  date: '2024-09-09',
  title: `Introducing Dynamic Suggested Questions`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: [],
  thumbnail: dynamicSuggestedQuestionsExample,
  preview:
    `
### 🔥 Why It Matters  

- ✅ **Personalized Experience** – Suggestions adapt to the user’s latest query for a more natural conversation flow.  
- ✅ **Increased Efficiency** – Users can quickly select relevant questions instead of typing them out.  
- ✅ **Higher Engagement & Conversions** – Contextually appropriate options guide users toward meaningful interactions.  
- ✅ **Seamless Updates** – No need to manually update static question sets—our AI handles it dynamically!  
- ✅ **Better User Experience** – Minimize irrelevant or repetitive suggestions to keep conversations smooth.  

### 🛠️ **How to Enable?**  
Simply go to **Interface Settings** and turn on **Dynamic Suggested Questions** to activate it instantly!  

### 💬 **Where Will These Appear?**  
- 🔹 **Chat Widget:** Up to four real-time suggested questions will display inline, adapting to the conversation.  
- 🔹 **Messenger:** For Facebook Messenger, quick replies will be shown (limited to 20 characters due to platform constraints).  

🔗 **Learn More:** [Dynamic Suggested Questions Documentation](https://cookbook.chat-data.com/docs/dynamic_suggested_questions)
`,
};


We’re thrilled to launch **Dynamic Suggested Questions**, a game-changing feature designed to make chatbot interactions more **intuitive, engaging, and personalized**!  

### 🔥 Why It Matters  

- ✅ **Personalized Experience** – Suggestions adapt to the user’s latest query for a more natural conversation flow.  
- ✅ **Increased Efficiency** – Users can quickly select relevant questions instead of typing them out.  
- ✅ **Higher Engagement & Conversions** – Contextually appropriate options guide users toward meaningful interactions.  
- ✅ **Seamless Updates** – No need to manually update static question sets—our AI handles it dynamically!  
- ✅ **Better User Experience** – Minimize irrelevant or repetitive suggestions to keep conversations smooth.  

### 🛠️ **How to Enable?**  
Simply go to **Interface Settings** and turn on **Dynamic Suggested Questions** to activate it instantly!  


### 💬 **Where Will These Appear?**  
- 🔹 **Chat Widget:** Up to four real-time suggested questions will display inline, adapting to the conversation.  
- 🔹 **Messenger:** For Facebook Messenger, quick replies will be shown (limited to 20 characters due to platform constraints).  
🔗 **Learn More:** [Dynamic Suggested Questions Documentation](https://cookbook.chat-data.com/docs/dynamic_suggested_questions)  

Ready to enhance your chatbot’s responsiveness? **Enable Dynamic Suggested Questions today!** 🚀

Introducing Dynamic Suggested Questions

export const article = {
  author: 'Samuel Su',
  date: '2024-09-02',
  title: `Introducing QR Code Sharing`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['qr code', 'sharing', 'chatbot', 'widget', 'iframe', 'customization', 'branding'],
  thumbnail,
  preview:
    `
We’re excited to launch a **new way to share your chatbot effortlessly—QR Code Sharing!** Now, you can generate a QR code for your chatbot and let customers connect with you instantly by simply scanning it.  

### 📌 Why Use QR Codes?  

- 🔹 **Instant Access** – Customers can connect with your chatbot in seconds.  
- 🔹 **Personalized Experiences** – Gather insights to enhance user engagement.  
- 🔹 **Cost-Effective Support** – Automate FAQs and routine queries to save resources.  
- 🔹 **24/7 Availability** – Provide seamless support anytime, anywhere.  
- 🔹 **Versatile Applications** – Use it for product info, bookings, feedback, and more.  
- 🔹 **Enhanced Marketing** – Run loyalty programs and promotions with ease.  

### 🔧 How to Get Started?  

1️⃣ **Generate Your QR Code** – Click the **"Share"** button in your chatbot dashboard, and your QR code will be created automatically.  
2️⃣ **Download the QR Code** – Save it in your preferred format.  
3️⃣ **Utilize It Across Channels** – Print it on business cards, product packaging, advertisements, digital displays, and more!  

By leveraging QR codes, you can **boost customer interactions, streamline operations, and grow your business effortlessly.**  
`,
};


We’re excited to launch a **new way to share your chatbot effortlessly—QR Code Sharing!** Now, you can generate a QR code for your chatbot and let customers connect with you instantly by simply scanning it.  

### 📌 Why Use QR Codes?  

- 🔹 **Instant Access** – Customers can connect with your chatbot in seconds.  
- 🔹 **Personalized Experiences** – Gather insights to enhance user engagement.  
- 🔹 **Cost-Effective Support** – Automate FAQs and routine queries to save resources.  
- 🔹 **24/7 Availability** – Provide seamless support anytime, anywhere.  
- 🔹 **Versatile Applications** – Use it for product info, bookings, feedback, and more.  
- 🔹 **Enhanced Marketing** – Run loyalty programs and promotions with ease.  

### 🔧 How to Get Started?  

1️⃣ **Generate Your QR Code** – Click the **"Share"** button in your chatbot dashboard, and your QR code will be created automatically.  
2️⃣ **Download the QR Code** – Save it in your preferred format.  
3️⃣ **Utilize It Across Channels** – Print it on business cards, product packaging, advertisements, digital displays, and more!  

By leveraging QR codes, you can **boost customer interactions, streamline operations, and grow your business effortlessly.**  

💡 **Ready to enhance your chatbot’s reach? Generate your QR code today!** 🚀

Introducing QR Code Sharing

export const article = {
  author: 'Samuel Su',
  date: '2024-08-26',
  title: `Introducing Business Profile Settings!`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['business profile', 'settings', 'social links', 'email', 'widget', 'iframe', 'customization', 'branding'],
  thumbnail,
  preview:
    `
We're excited to announce the launch of **Business Profile Settings**, a powerful new feature that lets you create a dedicated business profile within your chatbot widget.  

### 🌟 What's New?  

- 🔹 **Profile Description** – Showcase your business with a detailed description of your history, mission, and offerings.  
- 🔹 **Social Links** – Add up to 5 social media links to connect with your customers.  
- 🔹 **Action Items** – Display up to 5 key action links on your business profile page.  
- 🔹 **Flexible Display Options** – Choose whether to enable the business profile in an **iframe** or the chatbot **widget**. You can also set the **Business Profile as the first view** before the chatbot interface.  
- 🔹 **Direct Message to Email** – (Available on Standard plans and above) Enable customers to send messages directly to your registered email, ensuring no inquiry goes unnoticed.  

### 📌 How to Get Started?  
Head to **Your Business Profile Settings** to set up your profile and start engaging with customers in a more professional and personalized way!  

🔄 **Seamless Switching**: Customers can easily switch between the chatbot and the business profile interface with a single click on the top-left icon of the chatbot widget.  

This feature enhances your chatbot experience by making it easier than ever to **showcase your brand and engage with potential customers**.  

**Start setting up your Business Profile today!** 🚀  
`,
};


We're excited to announce the launch of **Business Profile Settings**, a powerful new feature that lets you create a dedicated business profile within your chatbot widget.  

### 🌟 What’s New?  

- 🔹 **Profile Description** – Showcase your business with a detailed description of your history, mission, and offerings.  
- 🔹 **Social Links** – Add up to 5 social media links to connect with your customers.  
- 🔹 **Action Items** – Display up to 5 key action links on your business profile page.  
- 🔹 **Flexible Display Options** – Choose whether to enable the business profile in an **iframe** or the chatbot **widget**. You can also set the **Business Profile as the first view** before the chatbot interface.  
- 🔹 **Direct Message to Email** – (Available on Standard plans and above) Enable customers to send messages directly to your registered email, ensuring no inquiry goes unnoticed.  

### 📌 How to Get Started?  
Head to **Your Business Profile Settings** to set up your profile and start engaging with customers in a more professional and personalized way!  

🔄 **Seamless Switching**: Customers can easily switch between the chatbot and the business profile interface with a single click on the top-left icon of the chatbot widget.  

This feature enhances your chatbot experience by making it easier than ever to **showcase your brand and engage with potential customers**.  


**Start setting up your Business Profile today!** 🚀

Introducing Business Profile Settings!

export const article = {
  author: 'Samuel Su',
  date: '2024-08-09',
  title: `Lazy Live Chat Triggering`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['live', 'chat', 'triggering', 'escalation'],
  thumbnail,
  preview: `
Introducing **Lazy Live Chat Escalation** - Smart control over when human support is triggered.

### Key Features

- **Smart Triggering:** Live chat button appears only when needed (e.g., chatbot can't answer, user requests human support)
- **Quick Setup:** Enable via **Settings > Live Chat** with customizable trigger conditions

### Dashboard & Notifications
- **Real-time Alerts:** Email and Zendesk notifications for escalation requests
- **Chat Management:** 
  - Filter by status (Unrequested/Unassigned/Open/Ended)
  - Track customer status and information
  - View chat history

### Communication
- **Automated Notifications:** Email alerts when either party sends messages while the other is offline
- **Dedicated Portals:** Separate URLs for agents and customers to continue conversations
- **Closed State:** Optional message when chat ends, prompting widget refresh

Enable this feature to ensure human support is available exactly when needed.
`,
};


**Lazy Live Chat Escalation Feature Launch!**

We're excited to introduce our new **Lazy Live Chat Escalation** feature, giving you more control over when live chat support is triggered. Now, instead of immediately displaying the live chat escalation button, you can set conditions to delay escalation until it's truly needed.

### What's New?

- **Easy Setup:**  
  Activate Lazy Live Chat Escalation by navigating to the **Live Chat** section under **Settings** and toggling on the feature. You can also customize the default triggering conditions to fit your workflow.



- **Delayed Escalation Trigger:**  
  Live chat escalation is activated only when specific conditions are met—such as when the chatbot doesn't have an answer or if the user explicitly requests human support.


- **Seamless User Experience:**  
  - The live chat escalation button is hidden until the preset conditions are satisfied.
  - Once the escalation is triggered, a dedicated live chat session begins.
  - After the live chat ends, you can display a **Closed State Message** to inform customers they need to refresh the chatbot widget for a new conversation.


### Handling Live Chat Escalation

- **Notifications:**  
  - Receive timely alerts via email or Zendesk ticket when a live chat escalation is requested.
  - Future updates will introduce SMS and app notifications for even faster alerts.
- **Live Chat Dashboard:**  
  Manage all escalated chats at your live chat dashboard:
  - **Retrieve chat history** within a specified date range.
  - **Filter chats** by status: Unrequested, Unassigned, Open, or Ended.
  - **View online status** indicators (green for active customers, red for offline) along with customer IP addresses, countries, and submitted lead information.


- **Enhanced Messaging Workflow:**  
  - **New Message to Customer:** When an agent responds after the customer has left the widget, an email notification is sent to the customer.
  - **New Message to Agent:** When a customer responds after the agent has exited the admin portal, the agent receives an email notification.

- **Dedicated Chat Portals:**  
  - **Agent Portal:** Use the unique URL provided in the notification to handle live chats in a dedicated admin portal (no login required, white-label friendly).
  - **Customer Portal:** Customers can also access their own dedicated portal via a unique URL to continue the conversation.

This feature offers you greater flexibility in managing live chat escalations—ensuring that human support is activated exactly when it's needed.

**Happy Chatting!**

Lazy Live Chat Triggering

export const article = {
  author: 'Samuel Su',
  date: '2024-07-25',
  title: `Sender Email White Labeling`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['email', 'white', 'labeling', 'chatbot'],
  thumbnail,
  preview:
    `
we are excited to launch the **Sender Email White Labeling** feature for you.

Previously, all our notification emails—including daily conversation summaries, daily leads summaries, live chat escalation notifications, and new message notifications—were sent from Chat Data's email address. This approach didn't align with the branding needs of our white labeling customers who wish to represent everything under their own brand.

**Introducing Email White Labeling**

If you are on our **Reseller** or **Professional** plan, you can now configure this feature by navigating to **Settings > White Labeling**. Follow these simple steps:

1. **Add a Customer Email:** Input the email address you want your notifications to be sent from.
2. **Update Your DNS:** Update your DNS settings as indicated in the provided table.
3. **Enjoy Rebranded Notifications:** All emails related to your chatbot will now be sent from your specified email address instead of Chat Data’s.

For example, a live chat escalation notification will now reflect your own brand’s email address, giving your communications a more personalized and professional touch.

We believe this enhancement makes white labeling more complete and thorough. Stay tuned—more email notification options will be added in the future to further enhance your branding impact.

`,
};


we are excited to launch the **Sender Email White Labeling** feature for you.

Previously, all our notification emails—including daily conversation summaries, daily leads summaries, live chat escalation notifications, and new message notifications—were sent from Chat Data's email address. This approach didn't align with the branding needs of our white labeling customers who wish to represent everything under their own brand.

**Introducing Email White Labeling**

If you are on our **Reseller** or **Professional** plan, you can now configure this feature by navigating to **Settings > White Labeling**. Follow these simple steps:

1. **Add a Customer Email:** Input the email address you want your notifications to be sent from.
2. **Update Your DNS:** Update your DNS settings as indicated in the provided table.
3. **Enjoy Rebranded Notifications:** All emails related to your chatbot will now be sent from your specified email address instead of Chat Data’s.


For example, a live chat escalation notification will now reflect your own brand’s email address, giving your communications a more personalized and professional touch.


We believe this enhancement makes white labeling more complete and thorough. Stay tuned—more email notification options will be added in the future to further enhance your branding impact.

Sender Email White Labeling

export const article = {
  author: 'Samuel Su',
  date: '2024-07-16',
  title: `Teams Management`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['team', 'management', 'collaboration', 'chatbot'],
  thumbnail,
  preview:
    `
We're excited to introduce **Team Management** for better chatbot collaboration!

### Key Features

- **Team Size Limits:** Free (0), Entry (5), Standard (20), Professional (1000) members
- **Access Management:** Manage team members through the **Settings > Members** tab

### Permission Levels
- **Read:** View configurations and chat
- **Train:** Train chatbot
- **Full:** Edit configurations, train, and integrate
- **Admin:** Full access plus member management
- **Owner:** Complete control with ownership transfer rights

### Quick Start
1. Go to **Settings > Members**
2. Click **Invite a member**
3. Enter email and set permissions

*Note: Invitees must have a Chat Data account*

Learn more about team management from our docs → [Invite Team Members](https://cookbook.chat-data.com/docs/invite-team-members)
`,
};


We’re excited to introduce our new **Team Management** feature—designed to help you collaborate more effectively on managing your chatbot!

### What’s New?

- **Invite & Collaborate:**  

- **Streamlined Management:**  
  Access the **Members** section via your chatbot’s **Settings** tab to view the current list of team members, their roles, and permission details.

- **Simple Invitation Process:**  
  - Click **Invite a member**.
  - Enter the member’s email address.
  - Select the appropriate permission level.
  - Hit **Invite** to send the invitation.  
  *Note: Invitations will work only if the invitee has signed up for Chat Data. Otherwise, they’ll receive a sign-up link, and you’ll need to invite them again once they’re registered.*

- **Flexible Permission Levels:**  
  Assign roles based on what your team member needs:
  - **Read:** View configurations and chat on the admin panel.
  - **Train:** Train the chatbot without altering configurations.
  - **Full:** Edit configurations, train the chatbot, and integrate with third-party platforms (cannot manage team members or delete the chatbot).
  - **Admin:** Full access plus the ability to invite/edit members and delete the chatbot.

- **Defined Roles:**  
  - **Owner:** Holds full access with admin privileges, including member management and the ability to transfer ownership.
  - **Member:** Operates within the permissions assigned.  
  *Remember: Only the Owner can transfer ownership, and the Owner automatically retains admin-level access.*
### Getting Started:

1. **Navigate** to your chatbot’s **Settings** tab.
2. **Access** the **Members** section.
3. **Invite** new members by clicking **Invite a member** and following the steps.

Learn more about team management from our docs → [Invite Team Members](https://cookbook.chat-data.com/docs/invite-team-members)

**Happy Collaborating!**

Teams Management

export const article = {
  author: 'Samuel Su',
  date: '2024-07-01',
  title: `Audio Input & Output Feature Launch!`,
  tagLink: 'insights',
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['audio', 'input', 'output', 'chatbot'],
  thumbnail,
  preview:
    `
### What’s New?

- **Speak & Hear:**  
  Users can now click the microphone icon in the chatbot widget—or in Messenger, WhatsApp, Instagram, Discord, and Slack integrations—to speak directly with your chatbot. Once the chatbot responds, simply click the text to hear the transcribed audio.

- **Multilingual Capabilities:**  
  - Audio input now supports **159 locales**.  
  - Enjoy responses with one of **519 voices across 152 locales**.  
  - Our multilingual voice detection and audio player ensure a seamless experience.

- **Customizable Settings:**  
  This feature is automatically enabled for all paid customers at no extra cost with these default settings:  
  - **Default Locales:** en-US, zh-CN, and es-ES  
  - **Default Voice:** en-US-RyanMultilingualNeural  
  To adjust your preferred locales (up to four for voice-to-text detection) and voices, simply go to **Settings > Chat Interface**. You can also disable the feature if desired.

### How It Works:

1. **Activate Audio:**  
   Click the microphone icon to speak with your chatbot.
2. **Multiplatform Support:**  
   Enjoy audio interactions across our chatbot widget and popular platforms like Messenger, WhatsApp, Instagram, Discord, and Slack.
3. **Listen to Responses:**  
   After receiving a text response, click on it to hear the audio output in your selected voice.
`,
};


We're excited to introduce our new **Audio Input and Output** capability, enabling your users to interact with your chatbot using their voice and hear responses in the voice of your choice.

### What’s New?

- **Speak & Hear:**  
  Users can now click the microphone icon in the chatbot widget—or in Messenger, WhatsApp, Instagram, Discord, and Slack integrations—to speak directly with your chatbot. Once the chatbot responds, simply click the text to hear the transcribed audio.

- **Multilingual Capabilities:**  
  - Audio input now supports **159 locales**.  
  - Enjoy responses with one of **519 voices across 152 locales**.  
  - Our multilingual voice detection and audio player ensure a seamless experience.

- **Customizable Settings:**  
  This feature is automatically enabled for all paid customers at no extra cost with these default settings:  
  - **Default Locales:** en-US, zh-CN, and es-ES  
  - **Default Voice:** en-US-RyanMultilingualNeural  
  To adjust your preferred locales (up to four for voice-to-text detection) and voices, simply go to **Settings > Chat Interface**. You can also disable the feature if desired.

### How It Works:

1. **Activate Audio:**  
   Click the microphone icon to speak with your chatbot.
2. **Multiplatform Support:**  
   Enjoy audio interactions across our chatbot widget and popular platforms like Messenger, WhatsApp, Instagram, Discord, and Slack.
3. **Listen to Responses:**  
   After receiving a text response, click on it to hear the audio output in your selected voice.

We believe this feature will greatly enhance the way users interact with your chatbot. As always, we appreciate your feedback—let us know how the new audio experience works for you!

**Happy Chatting!**

Audio Input & Output Feature Launch!

export const article = {
  author: 'Samuel Su',
  date: '2024-06-17',
  title: `WhatsApp Integration & Enhancements`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['whatsapp', 'integration', 'livechat', 'ai', 'customerservice'],
  thumbnail,
  preview: `
We're introducing a streamlined WhatsApp integration for Chat Data chatbots, offering enhanced control over customer communications.

## Key Features:

- **Dedicated WhatsApp Number:** Exclusive phone number for your chatbot
- **Quick Setup:** Simple Facebook-based integration process with 1000 free monthly messages
- **Alternative Integration:** System user access token method for advanced users
- **Live Chat Support:** Seamless handover from AI to human agents when needed
- **Smart Pause Feature:** Automatically route messages to email during initial setup

Get started by connecting your WhatsApp account through the Integrations tab on your Dashboard. Note: Your WhatsApp number must be exclusively dedicated to the chatbot service.
`,
};


We're excited to introduce new updates that streamline how you connect WhatsApp with your Chat Data chatbot. These enhancements not only simplify the integration process but also offer greater control and flexibility in managing customer communications.

## Key Updates:

- **Exclusive Phone Number Usage:**  
  - The WhatsApp phone number connected to your chatbot is now reserved exclusively for chatbot use—it cannot be used on WhatsApp or WhatsApp Business.
  - **Action Required:** If you are already using the number with WhatsApp, delete your account or disable two-step verification (for Meta Developer accounts) to free up the number.

- **Simplified WhatsApp Connection Process:**  
  - **Seamless Integration:** Navigate to Dashboard > [Chatbot] > Integrations and select the WhatsApp integration card.
  - **Embedded Signup Flow:**  
    1. Click **Connect** in the pop-up window.
    2. Sign in with your personal Facebook account.
    3. Click **Get started** and choose or create a business profile.
    4. Set up or select an existing WhatsApp business profile.
    5. Add a phone number (it's best to have just one associated number).
    6. Click **Continue**, allow for information verification, and then click **Finish**.
  - Enjoy up to 1000 free messages each month—add a payment method in Meta billing settings for additional messaging.

- **System User Access Token Signup Process:**  
  - **Fallback Integration:** In case you encounter Facebook authorization issues during the embedded signup:
    1. Develop your WhatsApp application following Meta's guidance.
    3. Go to the Integrations tab in your chatbot menu, click **Add to WhatsApp**, and enter your access token.
    4. Add and verify your phone number.
    5. Set up the callback URL in your WhatsApp App to subscribe to message events.

- **Live Chat Handover:**  
  - When the AI chatbot cannot provide a satisfactory response, you can take over with our live chat panel.
  - As a human agent, use the Live Chat dashboard or filter WhatsApp conversations to select the desired thread.
  - Turn off the AI chatbot for that conversation to ensure only your response is sent to the customer.
  - If the customer replies while you're offline, you'll receive an email with a link to the chat portal.

- **Automatic AI Chatbot Pause:**  
  - Configure an automatic pause (up to 1 week) during WhatsApp integration. During this period, customer messages bypass the AI and go directly to you via email notifications.
  - The AI chatbot will automatically resume after the specified duration.

## Get Started:
- **Existing WhatsApp Users:**  
  Follow the preliminary steps to delete your WhatsApp account or disable two-step verification so your number is free for integration.
- **New WhatsApp Integration:**  
  Simply head to the Integrations tab on your Dashboard and follow the guided steps to connect your WhatsApp account.

Check the [WhatsApp Integration](https://cookbook.chat-data.com/docs/whatsapp-integration) page for more details.

WhatsApp Integration & Enhancements

export const article = {
  author: 'Samuel Su',
  date: '2024-06-01',
  title: `Facebook Messenger Integration`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['messenger', 'integration', 'livechat', 'ai', 'customerservice'],
  thumbnail,
  preview:
    `
We're excited to introduce Facebook Messenger integration for your chatbot, enabling direct customer communication through your Facebook Pages. This update combines AI automation with human takeover capabilities and includes batch messaging support through our Make workflow template.

## Key Features:

- **Facebook Messenger Integration:**  
  - Connect your chatbot to Facebook Pages
  - Automated responses with human takeover option
  - Batch messaging support via Make workflow

- **Quick Setup:**  
  - Connect through Dashboard > [Chatbot] > Integrations
  - Select your Facebook Page and grant permissions
  - Test via QR code or INBOX link

- **Important Notes:**  
  - Access token requires renewal every 60 days (email reminder sent 10 days prior)
  - Switch between AI and human responses through Live Chat dashboard
  - Configure automatic AI pause (up to 1 week) during setup
  - Messages handled through INBOX (Facebook) won't sync with Chat Data
  - Offline notifications available through Chat Data's interface
`,
};


We're excited to introduce our latest integration that empowers your custom chatbot to connect directly with customers through your Facebook Pages. This powerful update not only automates responses but also gives you the flexibility to seamlessly take over conversations when needed, striking the perfect balance between efficiency and personal engagement. Plus, our new Make workflow template enables batch messaging for even more effective outreach.

## What's New:

- **Direct Communication via Facebook Messenger:**  
  - Connect your chatbot to your Facebook Pages and automate responses while retaining the ability for direct human takeover.
  - Leverage our Make workflow template to send messages in batches, expanding your reach to multiple customers simultaneously.

- **Streamlined Integration Process:**  
  - **Step 1:** Navigate to **Dashboard > [Chatbot] > Integrations** and select the Messenger integration card.
  - **Step 2:** Click the **Connect** button in the pop-up window.
  - **Step 3:** Grant permission for Chat Data to use your information (or choose **Edit Previous Settings** to modify your selection).
  - **Step 4:** Select the Facebook Page you want to connect and review the necessary permissions.
  - **Step 5:** Confirm the integration; a success message will appear along with your connected Facebook Page.
  - **Testing:** Scan the provided QR code or access the INBOX link to navigate to your Facebook Business Suite inbox for a live demo.

- **Manual Access Token Renewal:**  
  - **Important:** The Messenger integration requires manual renewal of the access token every 60 days.
  - You'll receive a notification email 10 days before the token expires. Renew manually to extend its validity for another 60 days.

- **Enhanced Live Chat Handover:**  
  - Switch from AI responses to direct human chat effortlessly:
    - Use the INBOX link or Chat logs Dashboard to access and respond to Messenger conversations.
    - If you have live chat enabled, select the conversation from the Live Chat dashboard or filter by Messenger conversations.
    - **Tip:** Turn off the AI chatbot for a conversation to ensure only your human response is sent.
  - When offline, if a customer responds while the AI is off, you'll receive an email with a link to the chat portal for prompt follow-up.

- **Automatic AI Chatbot Pause:**  
  - Configure an automatic pause (up to 1 week) during Messenger integration setup.
  - During the pause, customer messages bypass the AI and go directly to you via email notifications.
  - **Note:** This feature works exclusively with Chat Data's native live chat interface, as Facebook's Business Platform does not relay messages to Chat Data.

- **Understanding INBOX vs. Live Chat Dashboard:**  
  - **INBOX (Facebook Interface):** Messages sent here while the AI is off are managed by Facebook and will not be captured by Chat Data.
  - **Live Chat Dashboard (Chat Data Interface):** Offers offline email notifications when you're not available, ensuring you never miss a conversation.

Check the [Facebook Messenger Integration](https://cookbook.chat-data.com/docs/messenger-integration) page for more details.

Facebook Messenger Integration

export const article = {
  author: 'Samuel Su',
  date: '2024-05-17',
  title: `Facebook Instagram Integration`,
  avatar: '/images/samuel_su_profile.png',
  hashtags: ['instagram', 'integration', 'livechat', 'ai', 'customerservice'],
  thumbnail,
  preview:
    `
We're excited to introduce Instagram integration for your chatbot, enabling direct customer communication through your Instagram business account. This update combines AI automation with human takeover capabilities for efficient customer service.

## Key Features:

- **Instagram Integration:**
  - Connect your Business/Creator Instagram account
  - Automated responses with human takeover option
  - Requires Facebook Page connection

- **Quick Setup:**
  - Prerequisites: Instagram Professional Account + connected Facebook Page
  - Connect through Dashboard > [Chatbot] > Integrations
  - Link your Instagram and Facebook accounts
  - Test via QR code or INBOX link

- **Important Notes:**
  - Access token requires renewal every 60 days (email reminder sent 10 days prior)
  - Switch between AI and human responses through Live Chat dashboard
  - Configure automatic AI pause (up to 1 week) during setup
  - Messages handled through INBOX (Facebook) won't sync with Chat Data
  - Offline notifications available through Chat Data's interface

`,
};


We're excited to introduce a new integration that empowers your custom chatbot to communicate directly with customers through your Instagram account. This update automates responses while allowing seamless human takeover for a perfect balance of efficiency and a personal touch.

## What's New

- **Direct Instagram Communication:**
  - Connect your Business/Creator Instagram account with Chat Data to manage inquiries and deliver automated responses.
  - Enjoy flexible engagement—your chatbot handles routine questions, but you can step in any time for a personal response.

- **Step-by-Step Integration Process:**
  - **Prerequisites:**
    - An Instagram Professional Account.
    - A Facebook Page connected to your Instagram account.
  - **Integration Steps:**
    1. Go to **Dashboard > [Chatbot] > Integrations** and select the Instagram integration card.
    2. Click the **Connect** button in the pop-up window.
    3. Sign in with your Facebook account and click **Continue**.
    4. Agree to connect your Instagram account with Chat Data, then enter your Instagram username and password, and click **Get started**.
    5. Choose the Facebook Page you want to link with your Instagram account.
    6. Review the selected Facebook Page and Instagram account (ensure the **Allow access to messages** option is checked) and click **Next**.
    7. If it's your first time connecting, you might need to repeat the login process to properly add your Instagram account.
    8. Click **Continue** for the final permissions review, then hit **Save** to complete the integration.
  - Once complete, your chatbot is ready to respond to all messages received through Instagram.

- **Testing & Verification:**
  - Scan the provided QR code (using a different Instagram account) to test messaging with your Instagram bot.
  - Alternatively, use the INBOX link to access your Facebook Business Suite Instagram inbox and directly manage customer interactions.

- **Manual Access Token Renewal:**
  - The Instagram integration requires manual renewal of the access token every 60 days.
  - A notification email will be sent 10 days before the token expires. Renew it manually to extend its validity for another 60 days.

- **Enhanced Live Chat Handover:**
  - Use the INBOX link or Chat Logs Dashboard to switch from AI-driven responses to direct human intervention.
  - When taking over a conversation, turn off the AI chatbot to ensure only your human response is sent.
  - If a customer replies while you're offline, you'll receive an email notification with a link to the chat portal.

- **Automatic AI Chatbot Pause:**
  - Configure an automatic pause (up to 1 week) during the integration setup. During this pause, customer messages bypass the AI and are sent directly to you with email notifications.
  - **Note:** This feature works exclusively with Chat Data's native live chat interface—not with Facebook's Business Platform.

- **INBOX vs. Live Chat Dashboard:**
  - **INBOX (Facebook Interface):**  
    Messages sent while the AI is off won't be captured by Chat Data, and no offline email notifications are sent.
  - **Live Chat Dashboard (Chat Data Interface):**  
    Provides offline email notifications to ensure you never miss a customer message.

Check the [Instagram Integration](https://cookbook.chat-data.com/docs/instagram-integration) page for more details.

Claude Opus 4.5 Now Available

What's New

Key Improvements for Customer Support

Create Chatbots with your data

In just a few minutes, you can craft a customized AI representative tailored to yourself or your company.