Anthropic engineer: 90% of staff built self-prompting agent systems around Opus

joemeno · x · 2026-11-22

A shared video features an Anthropic engineer saying you're 'not supposed to prompt Opus 5.5 — you're supposed to build a system that prompts itself,' claiming 90% of Anthropic engineers have already done so. The 30min talk breaks down how Anthropic builds agents that remember, self-correct, and improve each run, with timestamps covering the markdown memory file they called 'unreasonably effective,' how one bad memory poisons an agent fleet, 'dreaming' agents, and the API behind self-improving agents. Quoted alongside: an article on the 5 levels of AI engineering (Prompt → Context → Harness → Loop → Graph).

Original post →

More from coding & agent

coding & agent channel →