{"id":"azure-samples-agent-architecture-review-sample","name":"agent-architecture-review-sample","af_score":47.0,"security_score":59.8,"reliability_score":30.0,"what_it_does":"An open-source sample “Architecture Review Agent” that accepts architectural descriptions (YAML/Markdown/plaintext/files), parses and/or uses LLM inference to produce a structured risk analysis and recommendations, and generates interactive Excalidraw diagrams (with PNG export). It can run as a local CLI, a FastAPI-based web app (custom REST endpoints), or as a Microsoft Foundry hosted agent exposing an OpenAI Responses-compatible `/responses` endpoint.","best_when":"You need quick, iterative architecture feedback and diagram generation from semi-structured inputs, and you can provide Azure OpenAI/Microsoft Foundry model access plus (optionally) an Excalidraw MCP server.","avoid_when":"You need strict determinism, formal verification, or strong privacy guarantees for highly sensitive content; also avoid using the Excalidraw MCP connection with SSL verification disabled except in tightly controlled environments.","last_evaluated":"2026-03-30T15:22:46.368922+00:00","has_mcp":true,"has_api":true,"auth_methods":["API key or Azure AD (for the Web App deployment)","Microsoft Foundry managed identity (for Hosted Agent deployment)","Azure OpenAI API key (for LLM inference; as configured in .env)"],"has_free_tier":false,"known_gotchas":["May require disabling SSL verification via ARCH_REVIEW_NO_SSL_VERIFY to work in certain corporate proxy scenarios—this can weaken security if used broadly.","LLM inference paths can produce variable results; outputs depend on input quality and model deployment.","No explicit mention of rate limiting behavior, retry/idempotency semantics for API calls, or structured error codes in the provided README excerpt."],"error_quality":0.0}