Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMind
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
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.
sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
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.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Why it matters
It argues, with a live demo stripping code with each pass, that agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → files, an AGENTS.md, and a hosted sandboxAn isolated environment where AI-generated code or agent actions run without being able to touch anything real.Full definition → can replace hand-written tool schemas and orchestration code, and that agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → complexity growing alongside model capability is a sign of overengineering.
videoWe let an AI agent execute Bash and lived to talk about it — Sarah Sanders, PostHog
videoNo Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, Oracle
videoHow We Solved Agent Building — Andrew Qu, Vercel
videoEvery step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate
