Decoding the new AI lingo: Loops, harnesses, squads, hill climbing… oh my!
Source
github.blog
Author
Cassidy Williams
Date
Context
An AI agentAn 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.Full definition →'s 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 → is the software surrounding its model: the tools it can call, permissions it receives, information it sees and workflow it follows. GitHub's terminology guide distinguishes that from a loop, which repeatedly runs work through steps such as fetching tasks, generating an answer, validating it and escalating problems. Improving an agent can therefore mean changing those surrounding steps or controls. The guide describes evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition →-driven adjustment of that system as hill climbing. Terminology guide.
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.
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.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
