• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
• grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.

Offers a grounded response to the anxiety of watching coding agents outperform years of hand-written work: the scarce skill was never syntax translation, and deep engineering judgment becomes more valuable as agents absorb implementation.

• articleQuoting Boris Chernysimonwillison.net
• articleResearch acceleration: The view inside OpenAIsimonwillison.net
• articleIntroducing GPT-6 Astra for developerssimonwillison.net

Checking sign-in…

Loading comments…