---
schema: 1
type: term
title: _harness_
description: >-
  In agent tooling, a **harness** is the scaffolding software that surrounds an
  AI model — the agent environment (such as Claude Code or Codex) through which
  the model runs, takes actions, and is evaluated. Harness choice measurably
  changes results: harnesses performed drastically differently on evals, and new
  models require harness and model to be very paired rather than
  interchangeable.
canonical: 'https://liquidgold.cc/channel/everyinc/explore/term/harness-d1b75c879d04'
markdown: 'https://liquidgold.cc/channel/everyinc/explore/term/harness-d1b75c879d04.md'
llms: null
parent: 'https://liquidgold.cc/channel/everyinc/llms.txt'
channel: everyinc
updated: '2026-10-23T22:12:35.346Z'
language: null
children: []
---


# \_harness\_

Canonical: https://liquidgold.cc/channel/everyinc/explore/term/harness-d1b75c879d04

Parent: [Channel index](https://liquidgold.cc/channel/everyinc/llms.txt)

## Definition

In agent tooling, a **harness** is the scaffolding software that surrounds an AI model — the agent environment (such as Claude Code or Codex) through which the model runs, takes actions, and is evaluated. Harness choice measurably changes results: harnesses performed drastically differently on evals, and new models require harness and model to be very paired rather than interchangeable.

## What a harness is around an agent model In this channel's material, a **harness** is the agent scaffolding that surrounds an underlying model — the client-side software (think Claude Code, Codex, or similar agent environments) through which a model actually does its work. The model alone doesn't determine performance; the harness it's run inside matters just as much. When the Every team evaluates new models, harness choice is treated as part of the evaluation itself: harnesses performed _drastically differently_ on evals, so a model's results can't be read apart from the harness they came from [^4872db36-e98a-5f6b-bc5c-b11e48c9411b@813]. ## Harness and model are very paired A recurring theme is that you cannot hot-swap models into any harness and expect the same results. Katelyn Lesse notes that **new models require harness and model to be _very paired_** — tuning them together is what makes an agent setup perform well [^4872db36-e98a-5f6b-bc5c-b11e48c9411b@692]. That's why the channel's model vibe checks treat the harness as a caveat to understand before reaching for a model like Opus 4.8: its measured behavior reflects the harness it ran in, not the raw model alone. ## Harness engineering — and the harder wall Teams often expect **harness engineering** to be the bottleneck in shipping agents. Katelyn Lesse argues the real wall everyone hits is **production infrastructure** — keeping servers running, storing transcript data, and secure sandboxing [^4872db36-e98a-5f6b-bc5c-b11e48c9411b@1181]. The harness matters, but it isn't where most teams should expect to get stuck.  - A **harness** is the agent scaffolding around a model — the software layer through which the model acts. - Harnesses performed **drastically differently** on evals, so model results depend on the harness used. - New models need harness and model to be **very paired**, not hot-swappable. - Teams expect harness engineering to be the bottleneck, but **production infrastructure** is the real wall.