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.

Original post →

More from coding & agent

coding & agent channel →