Bob Martin Shares Agent Squad Orchestration: FSMs and Monte Carlo Testing
blaizedsouza · x · 2026-08-05
Uncle Bob Martin shared details about an orchestration harness he is building for a squad of agents. The system features a supervisor agent managing various worker agents, including analysts, reviewers, architects, and testers.
The workflow follows a fixed path from themes to code and architecture, described using a static Finite State Machine (FSM). He had the agents build the FSM and a simulator to test the squad. By injecting delays and failures and running Monte Carlo simulations, he evaluated the robustness of the system.
More from coding & agent
- Google Open-Sources Gemini API Skills, Boosting Agent Code Generation to 96% — patloeber · 2026-08-05
- Malicious GitHub Repo Disguised as Crypto Exploit Exposed via LLM-Assisted Review — RSync25 · 2026-08-05
- AI Agents Automate Competitor Analysis and Influencer Marketing Strategy — fekdaoui · 2026-08-05
- Opinion: AI Coding is Manageable, but AI Workflows Risk Becoming Slop Without QA — oran_ge · 2026-08-05
- /human-review: Give AI Feedback Like Editing a Google Doc — petergyang · 2026-08-05
- Developer Recreates Pacman Entirely from AI-Generated Binary Code — Dimillian · 2026-08-05