Dark software factory: humans stop reading code as agents build, verify and ship
Al_Grigor · x · 2026-10-20
Al Grigor distills his webinar with Hugo Bowne-Anderson into an "agentic engineering" playbook: humans submit specs, agents write and verify the code (tests, reviews, judges), and humans only validate artifacts like dashboards before making business calls.
Key practices covered:
- One agent reviewing another agent's code and designs
- Giving agents explicit rules for coding and writing
- Organizing agents into teams and larger hierarchies
- Running "dark factory" workflows where nobody reads the code
His thesis: it will soon be cheaper to stop reading code and focus on outcomes — though it's not for everyone.
More from coding & agent
- Factory adds Linear delegations, letting Droid agents run issues automatically — matanSF · 2026-10-21
- Agent memory, goals and emotion should be designed as one system, argues dev — mimi10v3 · 2026-10-21
- Meta launches Muse Wonder coding models with 1M context, $4/$20 per million tokens — AIatMeta · 2026-10-21
- CastWorkshop: open-source studio ties Ollama and ComfyUI into persistent AI characters — CastWorkshop · 2026-10-21
- Agents break in production for boring backend reasons, not model reasons — DayKnown1050 · 2026-10-21
- REA turns any site, app, or game into an RL environment via open-source AgentEnv — henloitsjoyce · 2026-10-21