Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite
Source
Mohsen Arjmandi
Author
Mohsen Arjmandi
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.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
Challenges the assumption that a vendor's native 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 → always beats generic ones: results split sharply by task type, so teams should benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → harness choice on their actual task distribution rather than trust vendor pairing by default.
articleHarness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven SystemsPaul Barbaste, Tristan Darrigol, Germain Vu, Tom Wiltberger
postThe Harness Is Everything: What Cursor, Claude Code, and Perplexity Actually BuiltRohit
postHarness design cut agent cost 40% across six labs' modelsWRITER