Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.duckie.ai/llms.txt

Use this file to discover all available pages before exploring further.

Agents are the AI assistants at the heart of Duckie. Each agent is a configured AI that handles customer conversations according to your instructions, resources, and deployment settings.

What is an Agent?

An agent is a complete AI assistant configured with:
  • Start mode — Autonomous, workflow, or runbook behavior
  • Instructions — The agent’s role, scope, and decision rules
  • Knowledge — Sources it can search for information
  • Guidelines — Rules for communication style and tone
  • Guardrails — Safety constraints and escalation rules
  • Tools — Actions it can perform (respond, search, escalate, call APIs)
Think of each agent as a specialized team member trained for specific types of support.

Agent Capabilities

Agents can:
CapabilityDescription
Respond to customersGenerate and send replies across Zendesk, Slack, Intercom, and more
Search knowledgeFind relevant information from your connected documentation
Follow proceduresExecute runbooks or workflows you define
Take actionsCreate tickets, update records, send messages, call APIs
EscalateHand off to humans when guardrails trigger
ClassifyTag conversations with categories and attributes

Start Modes

Every agent has a start mode:
ModeBest forHow it works
AutonomousOpen-ended support where the agent needs to choose what to research or doStarts from agent instructions and decides which runbooks, workflows, knowledge, and tools to use
WorkflowDeterministic processesStarts at a selected workflow and follows its nodes and branches
RunbookOne flexible procedureStarts from a selected runbook and follows its instructions

Autonomous Agents

Learn how to configure agents that decide which resources and tools to use at run time.

Agent Configuration

Knowledge Sources

Control what information the agent can access:
  • Leave knowledge tags empty to allow all connected and custom knowledge
  • Use knowledge tags to narrow what’s searchable
  • Mix connected sources with custom articles

Guidelines

Shape how the agent communicates:
  • Tone and voice (friendly, professional, casual)
  • Response format and length
  • Brand terminology and phrases
  • Domain-specific instructions

Guardrails

Define safety boundaries:
  • Escalation rules — When to hand off to humans
  • Restrictions — What the agent cannot do or say

Classification

Configure how conversations are tagged:
  • Categories (Billing, Technical Support, etc.)
  • Custom attributes (Priority, Product Area, etc.)

Multiple Agents

You can create multiple agents for different purposes:
StrategyExample
By teamBilling Agent, Technical Support Agent, Sales Agent
By channelSlack Agent (casual), Zendesk Agent (formal)
By customerEnterprise Agent (high-touch), Self-serve Agent
By productProduct A Agent, Product B Agent
Each agent can have completely different knowledge, guidelines, and behavior.

Agent vs Runbook vs Workflow

ConceptWhat It IsExample
AgentThe complete AI assistant with instructions, resources, tools, and deployment settings”Support Agent”
Autonomous modeA start mode where the agent decides which resources and tools to use”Research the issue, read relevant runbooks, call tools as needed, then respond”
RunbookFlexible instructions the agent follows”When a customer asks about refunds, verify their order, check eligibility, process or explain policy”
WorkflowVisual process with explicit steps and branchesStart → Check Order → Decision: Eligible? → Yes: Process Refund / No: Explain Policy
An agent can start autonomously, from a workflow, or from a runbook. It then combines that start mode with knowledge, guidelines, guardrails, tools, and deployment settings.

Next Steps

Create an Agent

Step-by-step guide to your first agent

Agent Configuration

Deep dive into all settings

Autonomous Agents

Configure flexible agents for open-ended conversations

Workflows

Learn about visual workflows

Runbooks

Learn about flexible, AI-driven runbooks