Lessons From Running a Software Factory: Agents Build, Humans Occasionally in the Loop
blaizedsouza · x · 2026-11-11
Andre Staltz shared highlights from a talk on running a Software Factory.
Definition: "A system of agents that build software, with humans occasionally in the loop—a higher layer of abstraction where your engineering craft gets poured into agent instructions and infrastructure, not into code."
Building blocks: on-demand agents, scheduled agents (underutilized), correct instructions (skills, rules), and the correct environment (cloud, infra, connectors).
Good motivations: less tedious work and mindless agent-nudging, eliminating slop, increasing trust. Poor ones: automating everything ASAP, just vibing, never looking at code.
More from coding & agent
- KAIST's WikiTrace: evidence-linked memory fixes agent "memory-induced degradation" — dair_ai · 2026-11-11
- Why inference speed will be AI products' biggest competitive edge in 1–2 years — itsOmSarraf_ · 2026-11-11
- What happened when I moved vector retrieval into Snowflake SQL instead of orchestrating RAG outside — dima806_dima · 2026-11-11
- OpenAI engineer runs Codex for 26 days straight hunting Atlantis, spawning "vibe archaeology" — Polymarket · 2026-11-11
- He replaced a $5,000/month ghostwriter with 11 Claude Skills and earned $47,000 from one post — aryanXmahajan · 2026-11-11
- Refero Styles ships 2,000+ DESIGN.md files to give Claude Code real design taste — bbssppllvv · 2026-11-11