Decoding the new AI lingo: Loops, harnesses, squads, hill climbing… oh my!
Source
Cassidy Williams
Author
Cassidy Williams
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.
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.
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.
Why it matters
Loop engineering, harnesses, and hill climbing are how teams are actually structuring 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 → work, and a shared definition of each makes it clear which are new patterns and which are renamed cron jobs.
