Basic Settings
Name & Description
- Name — Displayed throughout the app and in analytics
- Description — Help your team understand what this agent does
Status
Agents can be:- Active — Available for deployments and testing
- Archived — Hidden from lists, deployments disabled
Starting Logic
The starting logic defines how your agent handles conversations. Choose one:Runbook
A runbook is natural language instructions that guide the agent while allowing flexibility. When to use:- Conversations require judgment and adaptation
- Process has a general structure but varies by situation
- You want to leverage AI reasoning within guidelines
Workflow
A workflow is a visual graph that defines exact steps and branches. When to use:- Process must follow exact steps every time
- Compliance requires predictable, auditable execution
- Multiple tools must be called in a specific order
Knowledge Configuration
Control what information the agent can access when searching.Source Selection
Choose specific knowledge sources:- Toggle sources on/off individually
- Agent will only search selected sources
- Unselected sources are invisible to this agent
Tag Filtering
Alternatively, filter by knowledge tags:- Select tags to include
- Agent searches all articles with those tags
- More flexible than source selection
Strategy Tips
| Goal | Approach |
|---|---|
| Broad access | Select all sources or don’t filter by tags |
| Domain-specific | Use tags like “billing”, “technical” |
| Product-specific | Tag articles by product, filter per agent |
Guidelines
Assign guideline sections that shape how the agent communicates.Section Assignment
- Check sections to include
- Sections are combined when multiple are selected
- Order doesn’t matter — all selected guidelines apply
Common Sections
- Tone & Voice — How the agent should sound
- Formatting — Response structure and length
- Brand — Terminology and phrases
- Domain — Product-specific instructions
Guardrails
Define safety constraints that protect customers and your brand.Escalation Rules
Select rules that trigger handoff to humans:- Each rule defines a condition (e.g., “customer is angry”)
- When triggered, agent escalates instead of responding
- Multiple rules can be active simultaneously
Restrictions
Select hard limits on agent behavior:- Highest priority — checked before processing
- Define what the agent cannot do or say
- Provide alternative responses when triggered
Classification
Configure how the agent tags conversations for analytics.Categories
Select categories the agent should assign:- Agent picks one category per conversation
- Categories appear in breakdown analytics
- Leave unselected to disable category assignment
Attributes
Select attributes to extract:- Agent identifies values for each attribute
- Can be single or multi-select
- Attributes appear in analytics and can be used for filtering
Tools
Configure which tools the agent can use.Duckie Tools
Built-in capabilities (always available):- Responder — Generate and send responses
- Knowledge Search — Search the knowledge base
- Escalator — Hand off to humans
- Ask and Wait — Ask clarifying questions
App Tools
Tools from connected integrations:- Automatically available when integrations are connected
- Enable/disable specific tools per agent
- Examples: Update Zendesk ticket, Create Jira issue
Custom Tools
Your own HTTP-based tools:- Created in Build → Tools
- Enable per agent as needed
Advanced Settings
Conversation Memory
Configure how much conversation history the agent considers:- Full history — All messages in the conversation
- Recent messages — Last N messages only
- Summarized — AI-summarized context
Response Settings
- Max response length — Character or word limits
- Follow-up behavior — How to handle multi-turn conversations