{
 "schema_version": 1,
 "generated": "2026-10-19",
 "id": "google-research-harness2--test-harness-refinement-on-legal-tasks",
 "repo": "google-research/harness2",
 "repo_url": "https://github.com/google-research/harness2",
 "repo_slug": "google-research-harness2",
 "title": "Test whether harness edits lift your agent on legal tasks",
 "page_title": "How to test whether harness edits lift your agent on legal tasks with harness2",
 "summary": "Run one LAB legal-work task with refinement, then judge and report, to see if edits beat the base harness.",
 "who": "Legal-tech engineer whose agent drafts antitrust or competition analysis and who wants evidence that prompt and tool edits help",
 "problem": "You cannot tell if rewriting your agent's prompts and guardrails improves legal output without a repeatable before/after run.",
 "outcome": "A judged and reported result for one LAB task, with the adopted harness and reflection notes saved under runs/.",
 "steps": [
  "Install the benchmark: harness2-setup lab",
  "Check prerequisites: harness2-check --bench lab",
  "Refine one task: harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1",
  "Judge the result: harness2-judge --bench lab --k 1 --mode parallel",
  "Read the summary: harness2-report --bench lab --k 1 --mode parallel"
 ],
 "agent_prompt": "In google-research/harness2, run the LAB benchmark for one antitrust-competition task with --k 1 --mode parallel, then run harness2-judge and harness2-report with the same flags. Confirm judge and report used identical benchmark, k, mode and seed as the refinement run.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "Judge and report must use the same benchmark, executor, subset, --k, --mode and seed as the refinement run, and model-backed runs cost real API money, so keep --max-tasks at 1.",
 "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": false,
 "best": false,
 "score": 0.542,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/google-research-harness2/test-harness-refinement-on-legal-tasks/",
 "md": "https://dedupedai.com/use-cases/google-research-harness2/test-harness-refinement-on-legal-tasks/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."
}