{
 "schema_version": 1,
 "generated": "2026-10-19",
 "id": "google-research-harness2--audit-which-harness-edits-actually-stuck",
 "repo": "google-research/harness2",
 "repo_url": "https://github.com/google-research/harness2",
 "repo_slug": "google-research-harness2",
 "title": "Audit which harness edits were adopted and why",
 "page_title": "How to audit which harness edits were adopted and why with harness2",
 "summary": "Read the adopted harnesses and reflection notes from a run to learn which prompt or tool edits drove a gain.",
 "who": "Agent builder who wants to copy the winning edits into a hand-maintained harness instead of re-running refinement",
 "problem": "You get a better score but do not know which of the eight editable components changed or what lesson justified it.",
 "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": [
  "Finish a refinement run, for example: harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1",
  "Open the benchmark folder under runs/ and find the adopted harnesses and reflection notes.",
  "Compare the adopted harness against the base harness, component by component.",
  "Note which edits came from the general candidate versus the domain-specific candidate.",
  "Copy the edits you trust into your own agent setup."
 ],
 "agent_prompt": "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.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "45 minutes",
 "basis": "field",
 "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.",
 "category": "Software & DevOps",
 "tags": [
  "Software & DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Linux, Python 3.12 and uv for installation",
  "No credentials needed for the local demo (harness2-demo)",
  "Model-backed runs need Node.js 20+, the Google Cloud CLI, a Vertex AI project and model IDs in .env, and gcloud application-default login",
  "LAB needs Pandoc and Poppler; WorkBuddy-Bench needs Docker",
  "Model-backed benchmark runs incur API costs"
 ],
 "risk": "dual-use",
 "seen_in_the_wild": true,
 "best": true,
 "score": 0.727,
 "evidence": [
  {
   "platform": "x",
   "url": "https://x.com/i/web/status/2112193309238329415",
   "posted": "2026-10-19"
  },
  {
   "platform": "x",
   "url": "https://x.com/i/web/status/2112219976056914081",
   "posted": "2026-10-19"
  }
 ],
 "url": "https://dedupedai.com/use-cases/google-research-harness2/audit-which-harness-edits-actually-stuck/",
 "md": "https://dedupedai.com/use-cases/google-research-harness2/audit-which-harness-edits-actually-stuck/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly."
}