{
 "schema_version": 1,
 "generated": "2026-10-19",
 "id": "google-research-harness2--improve-office-web-code-agent-workbuddy",
 "repo": "google-research/harness2",
 "repo_url": "https://github.com/google-research/harness2",
 "repo_slug": "google-research-harness2",
 "title": "Boost an office, web or coding agent on WorkBuddy tasks",
 "page_title": "How to boost an office, web or coding agent on WorkBuddy tasks with harness2",
 "summary": "Refine an agent's harness on one WorkBuddy-Bench subset to see if office, web or code results improve.",
 "who": "Builder of an internal assistant that edits documents, browses, or writes code and wants a measurable harness upgrade",
 "problem": "Hand-tuning prompts for office, web and code tasks is guesswork with no consistent score to compare against.",
 "outcome": "A judged WorkBuddy run for one subset showing whether a Propose-Probe-Compose step beat the base harness.",
 "steps": [
  "Install the benchmark (needs Docker): harness2-setup wb",
  "Check prerequisites: harness2-check --bench wb --subset office",
  "Refine one task (inferred, adapting the LAB example to WorkBuddy): harness2 --bench wb --subset office --k 1 --mode parallel --max-tasks 1",
  "Judge and report with matching flags: harness2-judge --bench wb --subset office --k 1 --mode parallel",
  "Read the report: harness2-report --bench wb --subset office --k 1 --mode parallel"
 ],
 "agent_prompt": "In google-research/harness2, set up WorkBuddy-Bench with harness2-setup wb and run one task from --subset office with --k 1 --mode parallel, then judge and report with identical flags. Verify Docker is running first and that the subset flag is passed on every command after setup.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "2 hours",
 "basis": "field",
 "caveat": "WorkBuddy-Bench needs Docker and the --subset flag on every command after setup, and the README guide for WorkBuddy should be checked for the exact task-selection flags before running.",
 "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": false,
 "score": 0.645,
 "evidence": [
  {
   "platform": "x",
   "url": "https://x.com/i/web/status/2112341275932586114",
   "posted": "2026-10-20"
  }
 ],
 "url": "https://dedupedai.com/use-cases/google-research-harness2/improve-office-web-code-agent-workbuddy/",
 "md": "https://dedupedai.com/use-cases/google-research-harness2/improve-office-web-code-agent-workbuddy/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."
}