Skip to main content
An agent architecture is the shape of your Duckie system: which agent owns the work, what process it follows, what tools it can use, when it delegates, and where humans stay involved. Start with the business process, not the Duckie object. Ask what needs to happen, what must be controlled, where judgment is useful, and what should be reviewed before customers are affected.

Quick Recommendations

If the work looks like thisStart with
Many customer topics enter one queueAn Autonomous agent with clear scope and guarded tool access
The same exact steps must happen every timeA Workflow
There is a known procedure, but conversations varyA Runbook
One part needs a specialistA parent agent or workflow with a sub-agent
The source, event, tag, or schedule already identifies the taskA targeted Deployment
The action is risky or policy-sensitiveGuardrails, approvals, or human review before Live mode

The Core Decision

Duckie systems work best when each part has a clear job:
  • Deployments bring work in from channels, webhooks, events, and schedules.
  • Agents own customer-facing or internal work.
  • Workflows control known steps, routing, approvals, and exact tool order.
  • Runbooks give flexible procedural guidance.
  • Sub-agents handle focused specialist tasks.
  • Tools read information, send messages, update systems, or call your APIs.
  • Guardrails define when Duckie should stop, avoid something, or involve a human.
  • Runs show what happened so you can debug and improve.
A good design often uses a workflow backbone for predictable process logic, with agents at the points where judgment, language, or research matters.

Questions to Ask

How predictable is the process?

Use a Workflow when the process should follow the same path, checks, and branches each time. Use a Runbook when the procedure is known but the conversation needs flexibility. Use an Autonomous agent when the request may require research, choosing between resources, deciding which tool to call, or handling many possible topics.

Who owns the overall journey?

If the process has known states, approvals, retries, or routing, let a workflow own the journey. If the work is an open-ended customer conversation, let an autonomous agent own the journey. If the work is one focused procedure, a runbook may be enough.

Does the system need specialists?

Use Callable agents when a parent agent or workflow should keep ownership but a specialist should handle one part. Specialist agents are useful for billing, technical triage, account review, evidence drafting, or internal approvals.

How risky are the actions?

Limit write tools to the agents that need them. Use Testing mode, Internal notes only, No write actions, Restrictions, Escalation Rules, and tool approvals for sensitive actions.

How will you improve it?

Review Analyze > Runs, track Categories, Attributes, and Resolution Tracking, then test changes in Test > Playground, Test > Replay Chats, and Test > Batch Test.

Common Architectures

PatternUse it whenExample
Single autonomous agentOne broad queue needs flexible handlingGeneral support agent for common product and billing questions
Workflow-first processThe sequence must be controlledRefund eligibility, approval, and response
Runbook-led agentThe task follows a procedure but needs judgmentPassword reset troubleshooting
Workflow with specialist agentsThe process is known, but steps need judgmentIntake workflow calls a classification agent and evidence drafting agent
Human review pathThe next step affects money, access, data, or customer trustDuckie prepares an action and a teammate approves it
Scheduled internal agentWork happens on a recurring cadenceDaily run summary or escalation review

Example

For a refund process:
  1. A deployment starts when a refund request arrives.
  2. A workflow looks up the order and checks eligibility.
  3. A runbook guides policy-based customer messaging.
  4. A specialist agent reviews unusual edge cases.
  5. A human approves high-value exceptions.
  6. Analyze > Runs shows the final path, tool calls, outcome, and any escalation.

Agents

Learn what agents can do and how start modes work.

Workflows

Build deterministic process logic.

Runbooks

Write flexible procedures for agents.

Designing Agent Systems

See advanced system patterns.