Dev adds railway 'pointing and calling' safety ritual to AI agent workflows
menhguin · x · 2026-10-09
Developer menhguin shares that they like having their agents perform 'pointing and calling' — a safety technique from early-1900s Japanese railways where operators point at key indicators and verbally confirm their status to force focus and avoid mistakes, now standard across Japanese industry and Chinese railway regulations. Rémi Louf, replying, argues that most 'software factory' people have clearly never read a book about manufacturing processes, and that this knowledge transfers to software engineering more than ever. Importing the ritual into agent workflows amounts to adding explicit confirmation and checking to each execution step.
More from coding & agent
- Open-source Ix parses your repo into a persistent graph you can query instead of grepping — tom_doerr · 2026-10-09
- Temporal runs the Pi coding agent on durable execution to survive machine failures — francesc · 2026-10-09
- Zed CEO Nathan Soller: AI-generated unit tests are slop, integration tests are the right middle ground — zeeg · 2026-10-09
- Jev pitched as the fastest AI model for agents: millisecond decisions at near-zero cost — Arindam_1729 · 2026-10-09
- Devs debate whether LLMs should write tests: 'tests expose things memory can't hold' — ivan_bezdomny · 2026-10-09
- Musk shows Grok agent setting up 16 emulators on a handheld with one prompt — elonmusk · 2026-10-09