Anthropic engineer says agents should prompt themselves, not just Claude
blaizedsouza · x · 2026-07-29
A repost of an Anthropic engineer talk on building agents that remember, learn from mistakes, and progressively improve themselves.
- The core point is that you should not just “prompt Claude,” but design a system that prompts itself.
- The session reportedly walks through Anthropic’s agent-building approach in about 45 minutes.
- The post frames it as more valuable than a paid course for people learning to build agents.
Related event: Anthropic Engineers on Agents: Systems Need to Prompt Themselves(2 posts)→
More from coding & agent
- Connected steps are not a workflow: nobody designs the handoff — usehive · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Running PolyStrata + Cline coding agent on a $0-fancy laptop at ~90 tok/s — rpwoerk · 2026-10-16
- How do you attribute agent gains: model training or infrastructure? — jrxna · 2026-10-16
- Feed Claude your books, blogs and top engineers' code for claude.md — 'it now writes better code than me' — blaizedsouza · 2026-10-16
- Open-source /label plugin auto-names and colors Claude Code sessions in one step — hermanschutte · 2026-10-16