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).
More from coding & agent
- Gemini subscriptions may work in third-party agent harnesses starting December 2 — testingcatalog · 2026-11-22
- Agno's AgentOS guide: build a team agent platform from zero to production — pritisinghhhh · 2026-11-22
- Agents shouldn't know they have memory: background 'dreaming' beats save_memory tools — uriwa · 2026-11-22
- Background memory consolidation tied to compaction, with 3.5k-char budget and prompt-injection safeguards — uriwa · 2026-11-22
- Proactive Grok Bot setup: 28 of 34 weekly stops produce zero notifications — marcelmarais · 2026-11-22
- Google engineer: Using Antigravity via T3 Code won't get you banned — ACP is the official path — lxfater · 2026-11-22