Anthropic engineer: 90% of us build systems that prompt Opus 5.5 themselves
GregCook2011 · x · 2026-11-01
An Anthropic engineer's 30-minute walkthrough: "You're not supposed to prompt Opus 5.5 — you're supposed to build a system that prompts itself. At Anthropic, 90% of our engineers have already built these systems."
She shows how Anthropic builds agents that remember context, fix their own mistakes, and get sharper with every run. Shared alongside a "Harness Engineering" guide arguing most people optimize agents at the wrong layer — rewriting prompts instead of building the outer harness.
More from coding & agent
- Coding agent drives iPhone via mirroring to auto-configure shortcuts syncing data to another agent — gethackteam · 2026-11-01
- Alma open-sources its Relay Server for self-hosted, end-to-end encrypted remote access — dotey · 2026-11-01
- Fully vibe-coded browser CS 1.6 clone adds crates and skins, supports 16 players — TAbrodi · 2026-11-01
- MyCaisse ships a remote MCP server: agents read/write freely, money moves only after human approval — Glittering-Cup9298 · 2026-11-01
- GitHub Copilot CLI v1.0.106 fixes CRLF handling, GHES URLs, encoding and more — copilot-cli-release-app[bot] · 2026-11-01
- Simo Guard: a security layer that vet AI agent tool calls before execution — CIRRUS_IPFS · 2026-11-01