Agent architecture
Agent architecture assigns responsibility across models, deterministic code, tools, state stores, queues, human reviewers, and independently operated agents. A useful architecture makes control flow, trust boundaries, and recovery behavior visible before framework details.
Questions to answer
Resolve these before adding tools, frameworks, or automation.
- Where does control flow live: code, one agent, or multiple agents?
- Which state must survive retries, deployments, or handoffs?
- Which boundaries cross teams, credentials, networks, or legal responsibility?
Implementation lifecycle
Build the evidence in this order
- 01
Define
Map actors, systems, data, decisions, and side effects before choosing components.
- 02
Build
Implement one end-to-end path with explicit contracts at every boundary.
- 03
Verify
Exercise dependency failure, retry, duplicate, timeout, and degraded-mode scenarios.
Artifacts to maintain
- system context diagram
- decision record
- trust-boundary map
- failure matrix
Continue through AgentAtlas
Evidence ledger
Primary documentation behind this guide
Anthropic
Building effective agents
Composable workflow patterns, the workflow-versus-agent boundary, and the case for starting with simpler architecture.
A2A Project
A2A protocol specification
Architecture for communication between independently operated agents, including discovery, tasks, messages, artifacts, and security schemes.
Next topic
Agent product design