​

Instruct AI Agent

​

Why Behavior Configuration Matters

• Maintain brand voice - Ensure every response reflects your company’s tone and values
• Handle different scenarios - Respond appropriately whether users need sales info, technical support, or account help
• Use the right tools - Access search tables, web search, or escalation capabilities when needed
• Personalize interactions - Adapt responses based on user attributes like plan tier, location, or role
• Evolve continuously - Update behavior as your product and customer needs change

​

Understanding Profiles

• Guidance rules - Instructions for different scenarios
• Tool access - Which capabilities the AI can use
• LLM settings - Model selection and configuration
• Version history - Immutable record of changes

​

Profile Versioning

1. Edit your current profile to make changes
2. Build a new version when ready
3. Deploy the version to production
4. Previous versions remain available for rollback

​

Creating Effective Guidance

• Instructions - What the AI should do and how
• Audience - Which users this guidance applies to
• Tools - Which capabilities the AI can access
• Priority - Order matters - first matching guidance wins

​

Anatomy of a Guidance Rule

• Descriptive label for organization
• Example: “Sales Inquiries”, “Technical Support”, “Premium Customer Service”

• Natural language description of desired behavior
• Rich text editor with formatting support
• Reference tools using inline code: search_products
• Be specific about tone, detail level, and response format

• Select which capabilities this guidance can use
• Tools mentioned in instructions are auto-enabled
• Examples: search_web, search_products, offer_handoff

• Define which users this guidance applies to
• Use query builder to filter by attributes
• Leave empty for “everyone”

• Toggle guidance on/off without deleting
• Inactive guidance is skipped during conversations

​

Writing Instruction Templates

Good:
"Help users find products by asking clarifying questions about their needs,
budget, and preferences. Search the product catalog using `search_products`
and recommend 2-3 options with pros and cons for each. Keep responses
concise (under 150 words) and friendly."

Avoid:
"Help users find products."

"Use a professional yet warm tone. Address users by first name if available.
Avoid jargon unless the user demonstrates technical expertise. Use bullet
points for lists of features or steps."

"Before answering questions about pricing or availability, always search
the product catalog using `search_products`. For general product questions,
search the knowledge base first. Only use `search_web` if our internal
resources don't have the answer."

"If users ask about topics outside your expertise (legal advice, medical
recommendations, financial guidance), politely explain you can't help with
that topic and offer to connect them with appropriate resources using
`offer_handoff`."

"When explaining technical concepts, use analogies. For example, explain
API rate limits like: 'Think of API calls like ordering coffee - you can
make 1000 orders per hour, but if you try to order more, you'll need to
wait until the next hour starts.'"

​

Audience Targeting

​

Why Use Audiences?

• Tiered Support - Premium customers get different service than free users
• Regional Adaptation - Adjust responses for language, timezone, or local regulations
• Role-Based Behavior - Treat developers differently from business users
• Channel-Specific - Behavior varies by integration (website vs. Zendesk vs. Slack)

​

Creating Audience Rules

User → Plan → equals → "enterprise"
User → Location → starts with → "EU"
User → Email → ends with → "@company.com"

Conversation → Channel → equals → "zendesk"
Conversation → Topic → contains → "billing"
Message → Contains → "urgent"

Current Time → Hour → between → 9 and 17
Current Time → Day of Week → in → ["Monday", "Tuesday", "Wednesday"]

(User.plan = "enterprise" OR User.plan = "business")
AND
User.location starts with "US"

​

Tool Configuration

​

General Tools

• Search the internet for current information
• Use when: Product launches, news, real-time data
• Example: “What are the latest features in version 2.0?”

• Retrieve specific URLs for content
• Use when: Reading documentation, release notes, blog posts
• Example: “Summarize the changelog from our blog”

• Create email escalation to support team
• User reviews and confirms before sending
• Use when: Complex issues requiring human expertise

• Immediately transfer conversation to support
• No user confirmation required
• Use when: Urgent issues, compliance concerns, high-value customers

​

Search Tables

1. Navigate to Tools → Search Tables
2. Click Add Search Table
3. Configure:
   • Tool Name: How AI refers to it (e.g., search_products)
   • Description: When to use this tool
   • Select Table: Choose your configured table
4. Save

Tool Name: search_products
Description: Search our product catalog by category, price range, brand,
and availability. Use this when users ask about products, features, pricing,
or inventory.
Table: product_catalog

​

MCP Servers

1. Navigate to Tools → MCP Servers
2. Add Server with URL and authentication
3. Import Tools from the server
4. Configure approval requirements for each tool

​

Guidance Priority and Matching

1. Order in the list - Drag to reorder guidance rules
2. Active status - Only active guidance is considered
3. Audience match - User must match audience criteria
4. Tool availability - Required tools must be enabled

​

Organizing Guidance

1. Premium Support (audience: enterprise customers)
2. Billing Questions (audience: topic contains "billing")
3. Product Questions (audience: everyone)
4. General Assistant (audience: everyone, fallback)

1. Zendesk Private Mode (audience: channel = zendesk, mode = private)
2. Zendesk Public Mode (audience: channel = zendesk, mode = public)
3. Website Chat (audience: channel = web)
4. Slack Internal (audience: channel = slack)

1. Sales Inquiries
2. Technical Support
3. Account Management
4. Onboarding
5. General Questions

​

Building and Deploying

​

Build Process

1. Make Changes - Edit guidance, tools, or settings
2. Review - Check “Unsaved Changes” indicator
3. Build Version - Creates new immutable profile version
4. Wait - System processes changes and creates deployment
5. Deploy - Set new version as active in production

​

Build Options

• Creates new version and deploys to production immediately
• Recommended for most updates
• Takes 30-60 seconds

• Creates version without deploying
• Use when: Testing changes before going live
• Deploy manually later from General tab

• For large deployments affecting many channels
• Receive email notification when complete
• Use when: Major behavior changes, many integrations

​

Deployment Status

• Green indicator: AI has latest knowledge
• Orange indicator: Knowledge sources updated, rebuild needed

• Orange indicator: Edits not yet built
• Build required to save changes

• Gray indicator: No pending edits

​

Best Practices

​

Start Simple, Iterate

Name: Customer Support Assistant
Instructions: Help customers with product questions, account issues,
and general inquiries. Use a friendly, professional tone. Search our
knowledge base and product catalog before answering. Offer to escalate
complex issues to our support team.
Audience: Everyone
Tools: search_web, offer_handoff

​

Test Before Deploying

1. Enter test messages
2. Observe AI responses
3. Verify tool usage
4. Adjust instructions
5. Build and deploy when satisfied

​

Monitor and Improve

1. Review conversations - Check real interactions in Analyze
2. Identify gaps - Where does guidance need refinement?
3. Update instructions - Make targeted improvements
4. Redeploy - Build new version with fixes

​

Use Clear Language

• Be explicit about expectations
• Provide examples of good responses
• Explain why certain approaches work
• Define edge cases and how to handle them

​

Leverage Tool Mentions

"Search for relevant help articles using `search_knowledge_base`. If no
articles match, try `search_web` for general information."

​

Version Strategically

• Significant behavior changes
• New tool additions
• Audience targeting updates
• Tone or style adjustments

• Minor wording tweaks (combine several into one version)
• Experimental changes (test in preview first)

​

Common Patterns

​

Pattern 1: Tiered Customer Support

Guidance 1: Enterprise Support
Instructions: "Provide detailed, comprehensive answers. Proactively offer
resources and best practices. Use `search_advanced_docs` for technical
details. Always offer to schedule a call with our success team."
Audience: User.plan = "enterprise"
Tools: search_advanced_docs, search_web, offer_handoff

Guidance 2: Standard Support
Instructions: "Help users solve common issues efficiently. Point to
documentation and guides. Escalate complex issues to support team."
Audience: Everyone
Tools: search_docs, offer_handoff

​

Pattern 2: Sales vs. Support

Guidance 1: Sales Assistant
Instructions: "Focus on product benefits and use cases. Highlight features
relevant to user's industry. Offer demos and trials. Use `search_case_studies`
to show customer success stories."
Audience: User.is_customer = false
Tools: search_products, search_case_studies, search_web

Guidance 2: Customer Support
Instructions: "Help customers use the product effectively. Answer how-to
questions and troubleshoot issues. Search documentation first."
Audience: User.is_customer = true
Tools: search_docs, search_products, offer_handoff

​

Pattern 3: Channel-Specific Behavior

Guidance 1: Zendesk Agent Assist
Instructions: "You're assisting support agents, not end customers. Provide
concise, factual information agents can relay to customers. Include ticket
number references and knowledge base links."
Audience: Channel = "zendesk", Mode = "private"
Tools: search_docs, search_tickets

Guidance 2: Website Chat
Instructions: "Engage directly with website visitors. Be welcoming and
helpful. Qualify leads by understanding their needs before recommending
solutions."
Audience: Channel = "web"
Tools: search_products, search_web, offer_handoff

​

Pattern 4: Regional Compliance

Guidance 1: EU Data Privacy
Instructions: "When discussing data handling, emphasize GDPR compliance.
Provide links to privacy policy. Never share specific customer data without
explicit consent. Offer to connect users with data protection officer."
Audience: User.region starts with "EU"
Tools: search_privacy_docs, offer_handoff

Guidance 2: General Region
Instructions: "Answer data and privacy questions using standard privacy
policy. Focus on security measures and data protection."
Audience: Everyone
Tools: search_privacy_docs

​

Troubleshooting

​

AI Not Using the Right Guidance

• Check audience filters - user might not match criteria
• Verify guidance is active (toggle on)
• Review guidance order - a general rule might match first
• Ensure required tools are enabled
• Check instruction clarity - be more explicit

​

Tools Not Available

• Verify tool is checked in allowed_tools for the active guidance
• Confirm tool is enabled in Tools tab
• For search tables, ensure table exists and has data
• For MCP servers, check connection status
• Rebuild profile to apply tool changes

​

Inconsistent Responses

• Tighten instructions to reduce variability
• Provide specific examples of desired responses
• Use search tables instead of general knowledge for facts
• Add explicit rules for edge cases
• Review conversation history to identify patterns

​

Build Failures

• Check for TODO items in advanced configuration
• Verify all required fields are filled
• Ensure at least one guidance exists (or system prompt in advanced)
• Review error message for specific issue
• Contact support if error persists

​

Knowledge Out of Date

• Rebuild profile to use latest knowledge snapshots
• This happens when data providers sync new content
• Build process incorporates latest knowledge into deployment

​

Next Steps

• Improve Answers - Refine responses based on real conversations
• Configure Escalations - Set up handoff workflows for human support
• Deploy Your AI - Make your configured AI available to users
• Review Conversations - Monitor how your guidance performs