agent-architecture

1# AI Agent Architecture
2 
3Help the user obtain a justified architecture for their task or an evidence-based audit of an existing agent. Deliver architectural decisions and ways to verify them, without implementing the agent. By default, completed work includes a PDF report and a visualization of the results. An “ideal architecture” fits the requirements, cost of failure, and team resources; it does not maximize the number of components.
4 
5## Choose a route
6 
7| Request | Route | Read |
8|---|---|---|
9| New agent, requirements are not yet clear | Design: working cases → early design → requirements and decision coverage → delivery | [design.md](references/design.md), [architecture-contract.md](references/architecture-contract.md) |
10| Architecture from an existing specification | Design: fill in what is known and clarify only gaps | The same files; do not restart the interview |
11| Review an agent already written | Audit: reconstruct actual paths → verify → deliver findings | [audit.md](references/audit.md), and [architecture-contract.md](references/architecture-contract.md) as criteria |
12| Agent makes mistakes, has degraded, or falsely reports “done” | Diagnosis within the audit: case → hypotheses → discriminating checks → correction and closure criterion | audit.md and [diagnostic-review.md](references/diagnostic-review.md) |
13| Review and redesign | Audit first; its demonstrated problems become design inputs | audit.md first, then design.md |
14…