Anthropic engineer: stop prompting Claude, build a system that prompts itself
s_mohinii · x · 2026-09-30
A widely shared post quotes an Anthropic engineer's 45-minute talk: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." The talk covers how agents remember context, fix their own mistakes, iterate on work, and improve across repeated runs, with an accompanying build guide.
More from coding & agent
- New Yorker-style illustration Skill hits 400 stars, monetizes via Baidu agent ecosystem — oran_ge · 2026-09-30
- Dev builds a Grok-powered 'X newsroom' that saves 3 hours a day on posting — jamestagg · 2026-09-30
- Dimillian hails new Codex cloud environments as fantastic, teases deep dive — Dimillian · 2026-09-30
- Agent kept claiming 'CRM updated' when it wasn't: a pragmatic external-verification fix — Kindly_Ganache9027 · 2026-09-30
- Omnigent v0.16.0 ships copy-on-write sandbox edits, unified workspace browser for AI agents — matei_zaharia · 2026-09-30
- Midas Touch code dataset questioned: no baselines, single seed, possible repo overlap — maier_ak · 2026-09-30