> ## Documentation Index > Fetch the complete documentation index at: https://docs.zappway.ai/llms.txt > Use this file to discover all available pages before exploring further. # AI Employee > Create intelligent AI Employees that automate customer interactions, qualify leads, and provide 24/7 support using your custom data and business logic. > **Important:** > AI Employees are autonomous agents that can handle conversations, access tools, retrieve knowledge, and perform actions on behalf of your organization. They learn from your data and adapt to your business needs. *** ## 🔢 Table of Contents 1. [What is an AI Employee?](#1-what-is-an-ai-employee) 2. [Creating Your First AI Employee](#2-creating-your-first-ai-employee) 3. [Configuring AI Employee Settings](#3-configuring-ai-employee-settings) 4. [Adding Knowledge with Datastores](#4-adding-knowledge-with-datastores) 5. [Connecting Tools](#5-connecting-tools) 6. [Deploying Your AI Employee](#6-deploying-your-ai-employee) 7. [Monitoring and Optimization](#7-monitoring-and-optimization) 8. [Best Practices](#8-best-practices) *** ## 1. What is an AI Employee? ### Overview An **AI Employee** (also called an Agent) is an intelligent virtual assistant that can: * Have natural conversations with users * Answer questions using your custom knowledge base * Perform actions through connected tools * Qualify leads and collect information * Transfer to human agents when needed * Work 24/7 across multiple channels **Key Capabilities:** * **Natural Language Understanding**: Comprehends user intent and context * **Knowledge Retrieval**: Searches datastores for accurate information * **Tool Usage**: Calls APIs, submits forms, generates leads * **Multi-Channel**: Works on web chat, WhatsApp, Messenger, Telegram, and more * **Handoff to Humans**: Seamlessly transfers complex cases to your team * **Continuous Learning**: Improves from conversations and feedback ### Common Use Cases **Customer Support:** * Answer FAQs automatically * Troubleshoot common issues * Guide users through processes * Escalate to human agents when needed **Sales & Lead Generation:** * Qualify inbound leads * Schedule demos and meetings * Answer product questions * Collect contact information **Internal Operations:** * HR assistance for employees * IT helpdesk automation * Policy and documentation lookup * Onboarding support **E-commerce:** * Product recommendations * Order tracking * Return and refund assistance * Shopping guidance *** ## 2. Creating Your First AI Employee ### Quick Start **Steps:** 1. Navigate to **AI Employees** in the sidebar (or visit `/agents`) 2. Click **"Create AI Employee"** button 3. Fill in basic information: * **Name**: Descriptive name (e.g., "Customer Support Bot", "Sales Assistant") * **Description**: Purpose and responsibilities * **Avatar**: Optional profile image 4. Click **"Create"** ### Initial Configuration After creation, you'll see the AI Employee detail page with several tabs: * **Overview**: Basic info and quick stats * **Settings**: Core configuration options * **Tools**: Connected integrations and capabilities * **Analytics**: Performance metrics and insights * **Debug**: Conversation logs and troubleshooting ### Naming Best Practices **Good Names:** * "Customer Support Agent" * "Lead Qualifier - Sales" * "HR Assistant Bot" * "Technical Support AI" **Avoid:** * Generic names like "Bot 1" or "Agent" * Names without context * Overly long names *** ## 3. Configuring AI Employee Settings ### General Settings **Name:** * Display name shown to users * Can be changed anytime * Keep it professional and clear **Description:** * Internal notes about the AI Employee's purpose * Helps team members understand its role * Not visible to end users **Avatar:** * Profile image representing the AI Employee * Appears in chat interfaces * Recommended: 200x200px, JPG or PNG ### Instructions (System Prompt) The **Instructions** field is the most important configuration. This is where you define the AI Employee's personality, behavior, and capabilities. **What to Include:** 1. **Role Definition:** ``` You are a friendly customer support agent for Acme Corp. Your goal is to help customers quickly resolve issues. ``` 2. **Tone and Personality:** ``` Use a professional yet warm tone. Be patient and empathetic. Keep responses concise and helpful. ``` 3. **Capabilities:** ``` You can: - Answer questions about our products - Check order status - Process returns - Escalate to human agents for complex issues ``` 4. **Limitations:** ``` You cannot: - Process payments directly - Access customer credit card information - Make promises about delivery dates ``` 5. **Guidelines:** ``` Always greet users warmly. Ask clarifying questions if needed. Provide step-by-step guidance for technical issues. Offer to connect to a human agent if you cannot help. ``` **Example Complete Instructions:** ``` You are Alex, a customer support specialist for ZappWay. You help users with questions about our AI automation platform. PERSONALITY: - Friendly, professional, and patient - Use clear, simple language - Show empathy for user frustrations CAPABILITIES: - Answer questions about features and pricing - Guide users through setup processes - Troubleshoot common issues - Recommend relevant documentation - Collect information for complex issues PROCESS: 1. Greet the user warmly 2. Understand their question or issue 3. Search the knowledge base for accurate information 4. Provide clear, step-by-step solutions 5. Confirm the issue is resolved 6. Offer additional help if needed WHEN TO ESCALATE: - Technical bugs or errors - Billing or payment issues - Custom enterprise requests - User explicitly requests human agent Always end conversations by asking if there's anything else you can help with. ``` *** ### Model Selection **Available Models:** ## 🧠 OpenAI — GPT Models * GPT-5.4 * GPT-5.4 Mini * GPT-5.4 Nano * GPT-5.3 Chat Latest * GPT-5.3 Codex * GPT-5.5 * GPT-5.2 Chat Latest * GPT-5.2 Chat * GPT-5.2 * GPT-5.1 Chat * GPT-5.1 * GPT-5 Mini * GPT-5 Nano * GPT-5 * GPT-4o * GPT-4o Mini *** ## 🔶 Anthropic — Claude * Claude Opus 4.6 * Claude Sonnet 4.6 * Claude Opus 4.5 * Claude 4.5 Sonnet * Claude 4.5 Haiku * Claude 4 Sonnet * Claude 3.5 Sonnet * Claude 3.5 Haiku *** ## 🔵 DeepSeek * DeepSeek V4 Pro * DeepSeek V4 Flash * DeepSeek R1 * DeepSeek V3.2 *** ## 🟡 Google — Gemini * Google Gemini 3.5 Flash * Google Gemini 3.1 Pro * Google Gemini 3.1 Flash Image * Google Gemini 3.1 Flash Lite * Google Gemini 3 Pro * Google Gemini 3 Pro Image * Google Gemini 3 Flash * Google Gemini-Pro 2.5 * Google Gemini-Flash 2.5 * Google Gemini-Flash 2.0 *** ## 🔷 Meta — Llama * Meta: Llama-4 Maverick * Meta: Llama-4 Scout *** ## 🟣 Perplexity * Perplexity: Sonar-Pro *** ## ⚫ xAI — Grok * xAI: Grok 4.3 * xAI: Grok Build 0.1 * xAI: Grok 4 *** ## 🟤 Amazon — Nova * Amazon: Nova-Premier * Amazon: Nova 2 Lite *** ## 🟠 OpenRouter * MiMo-V2-Pro * MiMo-V2-Omni * MiniMax M2.7 *** ## 🟢 Mistral * Mistral Large 2512 * Mixtral 8x22B * Mixtral 8x7B * Mistral Small Creative *** ## 🫧 Liquid * Liquid: LFM 2 24B * Liquid: LFM2 8B *** > **Note:** > > * **GPT-5.4**: Latest and most capable model in the GPT-5 family > * **GPT-5.4 Mini / Nano**: Fast and cost-effective for simpler tasks > * **GPT-5** models do not support manual temperature adjustment — they come pre-configured with automatic temperature recognition *** **Recommendation:** * Start with **GPT-5.4 Mini** for most use cases * Use **GPT-5.4** for highly nuanced or complex conversations * Use **GPT-5.4 Nano** for high-volume, straightforward queries *** ### Temperature Setting Controls response creativity and consistency. **Range:** 0.0 to 1.0 * **0.0 - 0.3**: Very consistent, deterministic (good for factual Q\&A) * **0.4 - 0.7**: Balanced creativity and consistency (recommended) * **0.8 - 1.0**: More creative and varied (good for conversational AI) **Use Cases:** * **Customer Support**: 0.3 (needs consistent, accurate answers) * **Sales Assistant**: 0.6 (balance between personality and accuracy) * **Creative Writer**: 0.9 (more varied, engaging responses) > **Important:** > > * **GPT-5** models do not support manual temperature adjustment, as they come configured with automatic temperature recognition.. *** ### Visibility Settings Control who can interact with the AI Employee: * **Public**: Anyone with the link can chat * **Private**: Only authenticated users in your organization *** ## 4. Adding Knowledge with Datastores ### Why Add Knowledge? AI Employees can only answer accurately if they have access to relevant information. Datastores provide this knowledge. **Without Datastores:** * AI relies only on general training data * May provide outdated or incorrect information * Cannot answer company-specific questions **With Datastores:** * Answers based on your actual documentation * Always up-to-date with your content * Provides accurate, relevant information ### Connecting a Datastore **Prerequisites:** * At least one datastore created with content * See [Datastore Documentation](/datastore/get-started) for setup **Steps:** 1. Open AI Employee settings 2. Navigate to **Tools** tab 3. Click **"Add Tool"** 4. Select **"Datastore Tool"** 5. Choose datastores to connect: * Click **"Select Datastores"** * Choose one or multiple datastores * Click **"Save"** 6. Tool is now active **Multiple Datastores:** You can connect multiple datastores to one AI Employee: **Example:** * Product Documentation datastore * FAQ datastore * Policy Documents datastore The AI will search all connected datastores to find relevant information. ### Datastore Tool Configuration **Search Settings:** * **Max Results**: How many chunks to retrieve (default: 5) * **Similarity Threshold**: Minimum relevance score (0-1) * **Priority**: Which datastore to search first (if multiple) **Best Practices:** ✅ **Good:** * Connect focused, relevant datastores * Keep datastores updated regularly * Use 3-5 datastores max per AI Employee ❌ **Avoid:** * Connecting 10+ datastores (slows responses) * Including irrelevant content * Duplicate information across datastores *** ## 5. Connecting Tools ### Available Tools Tools extend your AI Employee's capabilities beyond conversation. **Core Tools:** #### Datastore Tool * Search knowledge bases for information * Required for: Answering company-specific questions * See: [Datastore Tool Guide](/agent/tools/datastore-tool) #### HTTP Tool * Make API requests to external systems * Required for: Integrating with custom services * See: [HTTP Tool Guide](/agent/tools/http-tool) #### Form Tool * Present and collect structured data via forms * Required for: Lead capture, ticket submission * See: [Form Tool Guide](/agent/tools/form-tool) #### Request Human Tool * Escalate conversation to human agent * Required for: Complex issues needing human touch * See: [Human Handoff Guide](/agent/human-handoff) #### Mark as Resolved Tool * Mark conversation as completed * Required for: Clean conversation management * See: [Mark as Resolved Guide](/agent/tools/mark-as-resolved-tool) #### Lead Generation Tool * Automatically create and qualify leads * Required for: Sales automation * See: [Lead Generation Guide](/agent/tools/lead-generation-tool) ### Adding Tools **Steps:** 1. Go to AI Employee → **Tools** tab 2. Click **"Add Tool"** 3. Select tool type from list 4. Configure tool settings 5. Click **"Save"** **Tool Configuration:** Each tool has specific settings. Example for HTTP Tool: * **Endpoint URL**: API endpoint to call * **Method**: GET, POST, PUT, DELETE * **Headers**: Authentication and content type * **Body Template**: Data to send ### Tool Usage Examples **Customer Support AI:** ``` Tools: - Datastore Tool (Help docs) - Request Human Tool (Escalation) - Mark as Resolved Tool ``` **Sales AI:** ``` Tools: - Datastore Tool (Product info) - Form Tool (Lead capture) - Lead Generation Tool - HTTP Tool (CRM integration) ``` **E-commerce AI:** ``` Tools: - Datastore Tool (Product catalog) - HTTP Tool (Order lookup API) - Form Tool (Return requests) ``` *** ## 6. Deploying Your AI Employee ### Deployment Options Once configured, deploy your AI Employee across channels: #### Web Chat Widget Embed on your website for instant support. **How to Deploy:** Floating chat bubble in corner of page Inline chat widget embedded in page **Use Cases:** * Website support * Product pages * Landing pages * Documentation sites #### Messaging Platforms Connect to messaging apps your customers already use. **Available Integrations:** Personal WhatsApp accounts WhatsApp Business API Facebook Page messaging Instagram Direct Messages Telegram bots Internal team chat #### E-commerce Platforms Customer support for Shopify stores #### API Integration Use ZappWay API for custom implementations. **See:** [API Reference](/api-reference/authentication) ### Testing Before Deployment **Checklist:** * [ ] Test conversations with AI Employee * [ ] Verify datastore retrieval works * [ ] Check tool executions (forms, APIs) * [ ] Test human handoff flow * [ ] Try edge cases and error scenarios * [ ] Confirm responses match instructions * [ ] Test on mobile devices (for web chat) **How to Test:** 1. Go to AI Employee detail page 2. Use **Test Chat** interface (right panel) 3. Try various user questions and scenarios 4. Check debug logs for tool usage 5. Refine instructions based on results *** ## 7. Monitoring and Optimization ### Analytics Dashboard Track AI Employee performance: **Key Metrics:** * **Total Conversations**: Number of chats handled * **Messages Sent/Received**: Activity volume * **Resolution Rate**: % of conversations resolved without human * **Average Response Time**: How fast AI responds * **Tool Usage**: Which tools are called most often * **Knowledge Base Hits**: Datastore search frequency **Location:** AI Employee → **Analytics** tab ### Debug and Logs View detailed conversation logs for troubleshooting: **What's Included:** * Full conversation transcripts * Tool calls and responses * Datastore searches and results * Error messages * Processing time for each step **How to Use:** 1. Go to AI Employee → **Debug** tab 2. Select a conversation from list 3. Review step-by-step execution 4. Identify issues (wrong tool, bad retrieval, etc.) 5. Adjust configuration accordingly **See:** [Debug Guide](/agent/debug) ### Conversation File Upload Users can upload files during conversations for context. **Supported Files:** * PDF documents * Images (JPG, PNG) * Text files * Word documents **Configuration:** Enable in AI Employee settings → **Allow File Uploads** **See:** [Conversation File Upload Guide](/agent/conversation-file-upload) ### Answer Sources Show users where information came from: **Benefits:** * Builds trust (citations visible) * Helps users find original docs * Improves transparency **Configuration:** Enable in AI Employee settings → **Show Answer Sources** **See:** [Answer Sources Guide](/agent/answer-sources) ### Message Suggestions Provide quick-reply buttons to guide conversations: **Example Suggestions:** * "Check order status" * "Return an item" * "Speak to a human" * "Product recommendations" **Configuration:** 1. AI Employee settings 2. **Message Suggestions** section 3. Add suggested messages 4. Save **See:** [Message Suggestions Guide](/agent/message-suggestions) ### Continuous Improvement **Regular Tasks:** **Weekly:** * Review conversation logs * Check resolution rates * Identify common failure points * Update datastores with new content **Monthly:** * Analyze analytics trends * Refine system instructions * Add new tools if needed * Update knowledge base comprehensively **Quarterly:** * Major instruction overhaul * Evaluate model performance * Consider fine-tuning * Review ROI and impact **See:** [Optimize AI Answers Guide](/agent/optimize-ai-answers) *** ## 8. Best Practices ### Instruction Writing **Be Specific:** ✅ **Good:** ``` When a user asks about pricing, always mention our 7-day free trial first, then provide pricing tiers with feature breakdowns. ``` ❌ **Avoid:** ``` Help users with pricing questions. ``` **Use Examples:** ``` Example conversation: User: "How much does it cost?" You: "Great question! We offer a 7-day free trial to get started. After that, we have three plans: - Growth: $29/month for up to 1,000 conversations - Pro: $99/month for up to 15,000 conversations - Enterprise: Custom pricing for unlimited conversations Which plan sounds right for you?" ``` **Define Boundaries:** ``` DO NOT: - Make promises about delivery dates - Offer discounts without approval - Share confidential information - Provide medical advice ``` ### Knowledge Base Organization **Structure Datastores Logically:** Instead of one massive datastore: * Create focused datastores by topic * Example: "Billing FAQ", "Product Docs", "Policies" **Keep Content Updated:** * Remove outdated information promptly * Add new content regularly * Version documentation clearly **Write for AI Consumption:** * Use clear headings * Break information into digestible sections * Include keywords users might search for * Avoid jargon without explanations ### Tool Configuration **Only Connect Necessary Tools:** * More tools = more complexity * AI must decide which tool to use * Start minimal, add tools as needed **Test Tool Integrations:** * Verify API endpoints work * Check authentication * Test error handling * Monitor API rate limits ### User Experience **Set Clear Expectations:** ``` "Hi! I'm Alex, your AI assistant. I can help you with: ✓ Product questions ✓ Order tracking ✓ Account issues For billing or technical bugs, I'll connect you to our team." ``` **Provide Fallback Options:** ``` "I'm not sure I can help with that. Would you like me to: 1. Connect you to a human agent 2. Search our help center 3. Try rephrasing your question" ``` **Confirm Actions:** ``` "I found your order #12345. Would you like me to: - Check its status - Process a return - Contact support about it" ``` ### Security and Privacy **Protect Sensitive Data:** * Don't include passwords or API keys in instructions * Use environment variables for credentials * Limit datastore access to necessary information * Comply with GDPR/privacy regulations **Rate Limiting:** Prevent abuse with rate limits: **Configuration:** 1. AI Employee settings 2. **Rate Limiting** section 3. Set limits per user/IP **See:** [Rate Limit Guide](/agent/rate-limit) *** ## 📞 Support & Resources ### Getting Help **In-App Support:** * Help button in dashboard * Live chat (available on Pro+ plans) **Documentation:** * [Tools Overview](/agent/tools/quick-start) * [Human Handoff](/agent/human-handoff) * [Fine-Tuning](/agent/fine-tuning) * [Debug Guide](/agent/debug) **Common Resources:** * [Widgets Documentation](/widgets/chatbot/bubble) * [Integration Guides](/integrations/whatsapp) * [API Reference](/api-reference/authentication) ### Feedback **Report Issues:** * Use feedback button in dashboard * Email: [support@zappway.ai](mailto:support@zappway.ai) * Include: * AI Employee ID * Conversation ID (if applicable) * Expected vs actual behavior *** ## ✅ Quick Reference ### Essential Actions | Task | Location | Action | | ------------------- | ----------------- | --------------------------- | | Create AI Employee | AI Employees page | "Create AI Employee" | | Edit Instructions | Settings tab | "Instructions" field | | Add Tool | Tools tab | "Add Tool" | | Connect Datastore | Tools tab | "Datastore Tool" → "Select" | | Test AI | AI Employee page | Right panel chat | | View Logs | Debug tab | Select conversation | | Deploy to Web | Widgets | Copy embed code | | Connect to WhatsApp | Integrations | WhatsApp setup | ### Configuration Checklist ``` ✓ Name and description set ✓ Avatar uploaded ✓ Instructions written clearly ✓ Model selected (GPT-5 recommended) ✓ Temperature configured (0.6 recommended) ✓ Datastore tool connected ✓ Knowledge bases populated ✓ Additional tools added as needed ✓ Tested with sample conversations ✓ Rate limits configured ✓ Deployed to target channels > **Important:** > - **GPT-5** models do not support manual temperature adjustment, as they come configured with automatic temperature recognition.. --- ``` *** **Last Updated:** March 2026\ **Platform:** ZappWay AI Employees