Anthropic engineer's course on running self-improving agents in loops, graphs and harnesses
A post relays an Anthropic senior engineer's claim that agents in loops, graphs and harnesses complete 8–10x more work than prompting, and points to a guide on Opus 5.5 loops and jev engineering.
Anthropic senior engineer: “Prompting is no longer the job. I run agents inside loops + graphs + harness — same model, same tokens, 8–10x more completed work.” Prompts → Agents → Loops → Graphs → Harness In this course he shows exactly how Anthropic builds a team of self-improving agents that plan, verify, and keep running without you. Worth more than every paid agent engineering course combined. Watch it today before it gets buried. Then read the full guide for Opus 5.5 loop + jev engineering ↓
This post quotes another post: x.com/beamnxw/status/2108101310515925217