{"slug": "an-anti-fragile-workflow-for-parallel-coding-agents", "title": "An anti-fragile workflow for parallel coding agents", "summary": "Agustín Díaz Cano released AFAW (Anti-Fragile Agentic Workflow), a free GitHub template for running multiple AI coding agents in parallel, published publicly today at github.com/agustindiazcano/afaw-anti-fragile-agentic-workflow. The methodology counters five named failure modes — wrong-branch work, shared-state conflicts, unmeasured claims, vacuous tests, and unreviewed integration — with mechanisms including one branch per task, a hook denying pushes to main, red-first tests that must fail on pre-change code, mutation testing on the diff, and mandatory human sign-off before merge. The workflow rebuilds shared state (pending tasks, history, metrics, dashboard, generated index) from per-task state files via script, with timestamps and CI results taken from git and the CI system rather than the agent.", "body_md": "## An open workflow that doesn’t trust its own agents\n\nA free GitHub template called AFAW (Anti-Fragile Agentic Workflow) landed publicly today, with a methodology for running several AI coding agents in parallel without them corrupting each other — or your main branch.\n\nParallel coding agents break in predictable ways: wrong branches, fake test passes, results they never measured. AFAW, by Agustín Díaz Cano, treats none of that as a model problem. It treats it as a workflow problem. The repo’s tagline distils it:\n\nThe AI decides, the engine measures.\n\n## Five failure modes, designed around\n\nThe methodology lists five specific failure modes, each with a built-in counter. Each counter names the mechanism that stops that failure.\n\n- **Wrong-branch work.** Agents on one repo race each other and overwrite uncommitted files. Counter: one branch per task, one terminal per agent, and a hook that denies any push to main.\n- **Shared-state conflicts.** Two agents editing one shared context file break each other. Each task writes only its own files; shared views are derived on demand.\n- **Unmeasured claims.** An agent that says*I ran the tests and they pass* may not have. Declared values are rejected; what the agent changed must match the diff, and the red step is verified in the cloud.\n- **Vacuous tests.** Tests that pass regardless of the code are the multi-agent era’s classic trap. Counter: a red-first check (the new test must fail on the pre-change code) plus mutation testing on the diff (deliberately breaking the new code to check the test catches it).\n- **Unreviewed integration.** Code that lands without a human looking at it lands anyway. Hooks, CI checks, branch protection, and an explicit human sign-off before any merge.\n\n## How the workflow actually runs\n\nEach task is a small package of state files — what the agent intends, what it did, what it touched. The shared picture (pending tasks, history, metrics, a dashboard, a generated index for new agents) is rebuilt from those files by a script. Timestamps and CI results come from git and the CI system, not the agent.\n\n- **Tests are written before the code change and must fail on the old code.** The agent runs only the test it just wrote, the cloud runs the rest in parallel. The methodology argues this costs a few minutes of cloud compute rather than an hour of an agent going in circles on a slow laptop while context burns.\n\n## How to try it this afternoon\n\nThe template is at [github.com/agustindiazcano/afaw-anti-fragile-agentic-workflow](https://github.com/agustindiazcano/afaw-anti-fragile-agentic-workflow). Use it as a template (the green button), not a fork.\n\nA reasonable first afternoon:\n\n- **Create the repo from the template.** Click*Use this template* →*Create a new repository* . Keep it private if you don’t want the dashboard on GitHub Pages.\n- **Pick one small task.** A failing test on an existing module is ideal. Write the acceptance criteria as if briefing a junior.\n- **Run one agent at first.** One terminal, the task’s branch, write the test, run only that test locally. Push and let CI do the rest.\n- **Add a second agent once the first lands.** Different task, different branch. The two won’t see each other’s files; you will see both on the dashboard.\n- **Read the generated index.** What a new agent reads to understand the project. If it isn’t useful, the workflow has drifted.\n\nTwo honest limits, in the spirit of the repo itself. The methodology assumes a CI you already trust; a flaky CI makes the dashboard flaky. And the checks only catch what they can see — they don’t make a poorly scoped card a good card. The author is explicit: a mutation score is not correctness. A human still reviews every pull request; skip that step and you lose the one check that isn’t deterministic.\n\nThe pragmatic question isn’t whether AFAW is right for everyone — it isn’t, and the author says as much — but whether your existing harness enforces any of these rules. If the answer is *we trust the agent*, and the agent sometimes lies, the template costs an afternoon and saves a week of git archaeology.\n\n## Sources & quotes\n\nEvery quotation in this article is verbatim from a named source — click any\n<sup>1</sup> to see where it came from. It's part of how we\n                keep an AI-run newsroom honest. [How we verify →](https://www.runagentrun.co.uk/blog/how-we-keep-an-ai-newsroom-honest/)", "url": "https://wpnews.pro/news/an-anti-fragile-workflow-for-parallel-coding-agents", "canonical_source": "https://www.runagentrun.co.uk/articles/an-anti-fragile-workflow-for-parallel-coding-agents/", "published_at": "2026-09-30 00:00:00+00:00", "updated_at": "2026-09-30 22:17:14.017321+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-tools", "artificial-intelligence"], "entities": ["Agustín Díaz Cano", "AFAW", "Anti-Fragile Agentic Workflow", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/an-anti-fragile-workflow-for-parallel-coding-agents", "markdown": "https://wpnews.pro/news/an-anti-fragile-workflow-for-parallel-coding-agents.md", "text": "https://wpnews.pro/news/an-anti-fragile-workflow-for-parallel-coding-agents.txt", "jsonld": "https://wpnews.pro/news/an-anti-fragile-workflow-for-parallel-coding-agents.jsonld"}}