# How to audit which harness edits were adopted and why with harness2

Repo: [google-research/harness2](https://github.com/google-research/harness2) | Difficulty: Intermediate | Time: 45 minutes | Basis: Seen in the wild

Read the adopted harnesses and reflection notes from a run to learn which prompt or tool edits drove a gain.

**Who it is for:** Agent builder who wants to copy the winning edits into a hand-maintained harness instead of re-running refinement

**The problem:** You get a better score but do not know which of the eight editable components changed or what lesson justified it.

**The outcome:** A short list of concrete edits (system prompt, guardrails, memory, tool guidance and so on) with their stated evidence, ready to port by hand.

## Steps

1. Finish a refinement run, for example: harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1
2. Open the benchmark folder under runs/ and find the adopted harnesses and reflection notes.
3. Compare the adopted harness against the base harness, component by component.
4. Note which edits came from the general candidate versus the domain-specific candidate.
5. Copy the edits you trust into your own agent setup.

## Prompt to paste into your agent

```text
After a google-research/harness2 run on <benchmark>, open the runs/ folder and list every adopted harness edit grouped by component (system prompt, guardrails, memory, tool guidance, subagents, skills, scripts, plugins). Verify each edit has a matching reflection note before recommending I port it.
```

## Caveat

The README does not document the exact file layout inside runs/, so inspect the actual output folders rather than assuming a structure, and treat a single run's lessons as hypotheses.

## Seen in the wild

- X (Oct 2026): https://x.com/i/web/status/2112193309238329415
- X (Oct 2026): https://x.com/i/web/status/2112219976056914081

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/google-research-harness2/audit-which-harness-edits-actually-stuck/