Agent System Design
Choosing an Agent Architecture
Start with the business process, then choose agents, workflows, runbooks, sub-agents, and deployments.
Autonomous Agents vs Workflows vs Runbooks
Decide how much structure Duckie should follow for a given support process.
Single Agents vs Sub-Agents
Decide when one agent is enough and when to delegate focused work to specialist agents.
Routing and Orchestration Patterns
Choose where routing should happen: deployments, workflows, autonomous agents, or human review.
Operating Model
Context, Knowledge, and Memory
Understand what Duckie knows now, what it can look up, and what carries forward in a ticket.
Tools, Permissions, and Side Effects
Control what agents can do and how to test actions safely.
Guardrails, Escalation, and Human Review
Know when Duckie should continue, stop, ask for approval, or hand off to a teammate.
Workspaces and System Boundaries
Separate teams, products, regions, channels, permissions, and analytics with the right boundaries.
Testing, Observability, and Iteration
Use testing and analytics to launch safely and improve agent behavior over time.