Show HN: AFAW – A multi-agent coding workflow that doesn't trust the model

Category: devtools

Tags: multi-agent, ai-assisted-development, ci-cd, workflow, mutation-testing, deterministic

Score: 6.0/10 (Innovation: 6, Technical: 5, Documentation: 8, Utility: 5)

AFAW is a repository-level methodology and boilerplate for running multiple AI coding agents in parallel without collisions or unverified claims. It enforces deterministic measurement of results via CI, mutation testing, and branch protection, with a human approving every merge. The project includes a dashboard, state schemas, and a white paper.

Target audience: AI engineers, backend developers, devops teams using AI coding assistants

Repository: https://github.com/agustindiazcano/afaw-anti-fragile-agentic-workflow · Python · MIT

View on Hacker News