Skip to content

Agent Architecture Review Sample

The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.

Install

$git clone https://github.com/Azure-Samples/agent-architecture-review-sample

Install command taken from the project's README or registry entry. Always review code before running it.

Architecture Review Agent Sample

What is the Architecture Review Agent?

The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams - automatically. Feed it any architectural description (YAML, Markdown, plain text, code, design docs) and it returns a structured review with risk analysis, actionable recommendations, and an Excalidraw diagram you can edit and share.

For a structured docs map (setup, deployment, scripts, scenarios, testing), see docs/README.md.

Architecture

Clients (Teams/M365 Copilot, CLI, Web Browser) → Foundry Agent Service or Web App → Core Engine (Smart Parser, Risk Detector, Report Builder, Diagram Renderer, LLM Inference) → Azure OpenAI / Excalidraw MCP / ACR / Azure App Service

Internal Data Flow

flowchart TB
    subgraph Agent["Architecture Review Agent"]
        review_architecture
        infer_architecture
    end

    subgraph Tools["tools.py"]
        Parser["ParserYAML / MD / Plaintext"]
        LLMInference["LLM InferenceAzureOpenAIChatClient"]
        RiskDetector["Risk DetectorTemplate + LLM"]
        DiagramRenderer["Diagram RendererExcalidraw + PNG"]
        ComponentMapper["Component Mapper"]
        ReportBuilder["Report Builder"]
        MCPClient["MCP Client(Excalidraw Server)"]
    end

    review_architecture --> Tools
    infer_architecture --> Tools
    Tools --> LocalOutputs[".excalidraw / .png / .json"]
    MCPClient --> ExcalidrawMCP["Excalidraw MCP(Interactive View)"]

Why use it?

  • Instant architecture feedback - get a prioritised risk assessment and improvement plan in seconds, not days.
  • Works with what you already have - paste a YAML spec, drag in a README, or describe your system in plain English. The LLM infers structure when the input isn't formal.
  • Interactive diagrams - auto-generated Excalidraw diagrams render components, connections, and data flows. Edit them in-browser or export to PNG.
  • Two deployment options - run as a full-stack Web App (FastAPI + React) on Azure App Service, or as a Hosted Agent on Microsoft Foundry with Teams / M365 Copilot integration.
  • Built for developers - runs locally with a single script, deploys to Azure with one command, and exposes a REST API for pipeline integration.

Demo

Microservices Banking Architecture — full end-to-end review: file upload → risk detection → interactive Excalidraw diagram → recommendations.

If the video does not render inline, download and watch it here.


Features

Similar plugs

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

Explore related