Multi-Agent Code-Generation Orchestrator

Planner / Coder / Tester / Reviewer agents coordinated by an orchestrator with shared memory.

Prompt

Create a multi-agent code-generation orchestrator workflow diagram.

Layout:
- Center: Orchestrator block connected to four agents: Planner, Coder, Tester, Reviewer.
- Add shared memory / task state as a database-like block below the orchestrator.
- Show input requirements entering the Planner and final patch / pull request leaving the Reviewer.
- Show iterative loops: failed tests return to Coder, review comments return to Planner or Coder.
- Add small tool blocks for repository, terminal, browser, and CI logs.

Style:
- Clean software architecture diagram on white background.
- Navy main blocks, teal successful paths, coral feedback loops, amber tool-access accents.
- Use concise labels and directional arrows.
- Suitable for AI engineering papers, product docs, and system design explainers.

Use in Generator

When to use

For agentic-AI engineering papers describing structured code-generation or repair systems.

Variations

Two-agent Critic-Reviser

Simplify to two agents: Critic and Reviser. The Critic flags issues with the current patch; the Reviser produces a revision. The loop terminates when no issues are flagged.

Tips

Place external resources (vector memory, sandbox) outside the agent ring to keep the loop readable.
Label each arrow with its message type (plan / patch / test / revision). Generic arrows obscure the protocol.
Use a centered Orchestrator with radial layout. Linear pipelines miss the iteration story.

FAQ

How do I show parallel agent execution?

Add fork/join bars (horizontal thick lines) before and after the parallel section, and split arrows from the Orchestrator into multiple agents simultaneously.