Dev shares 4-step AI coding workflow: autonomous agents ship code with hourly health checks
gabe_ragland · x · 2026-11-02
Developer gaberagland outlines his current AI-assisted coding process:
- Planning: uses mattpocockuk's /grill-me prompt to plan new features;
- Build: agents build, review, and ship code without him in the loop;
- Monitoring: an hourly health check catches issues and auto-fixes them;
- Weekly review: a weekly code check analyzes PRs and threads, asking how architecture, tests, linting, and docs could reduce mistakes — even those already caught in review. This step stays human-in-the-loop.
He says it finally feels like a sane process and asks what others are doing.
More from coding & agent
- Reward hacking is Goodhart's Law for agents, warns Morgan Brown — morganb · 2026-11-02
- Debate on agentic commerce monetization: do agents really need payments revenue? — jeff_weinstein · 2026-11-02
- Veynod: open-source agent coding runtime with one model loop and a deterministic kernel — TKOWNS · 2026-11-02
- Claude Code subagents silently switch to paid usage, burning $100 in credits — nptacek · 2026-11-02
- Instinct reportedly blocked from WhatsApp as observers say agent pivot was predictable — itsOmSarraf_ · 2026-11-02
- Purser: an MCP server that lets agents pay with smart-contract limits a jailbreak can't bypass — Plane-Preference6245 · 2026-11-02