{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "metaevo-ai-harness-zero--generate-reviewed-agent-trajectories",
 "repo": "metaevo-ai/harness-zero",
 "repo_url": "https://github.com/metaevo-ai/harness-zero",
 "repo_slug": "metaevo-ai-harness-zero",
 "title": "Generate reviewed agent trajectories for training data",
 "page_title": "How to generate reviewed agent trajectories for training data with Harness Zero",
 "summary": "Run a harnessing agent over benchmark tasks and export successful trials as an SFT dataset.",
 "who": "An ML researcher who wants training trajectories for a small student model and has Docker and a model API key ready.",
 "problem": "Collecting agent trajectories by hand is slow, and raw runs without review do not carry the behaviors of an optimized harness.",
 "outcome": "A reviewed rollout directory of trial results and an sft.jsonl file built from trials that met the reward threshold.",
 "steps": [
  "Run `uv sync` in the cloned Harness Zero folder.",
  "Copy .env.example to .env and fill in the key for the model route you use.",
  "Create a task list with `printf 'uspto-train-000\\nuspto-train-001\\n' > /tmp/tasks.txt`.",
  "Run `harness-zero run-rollout --dataset data/uspto --components harness_bank/uspto --teacher-middleware-factory harness_bank.uspto.middlewares:build_teacher_middlewares --tasks-file /tmp/tasks.txt --attempts 1 --concurrency 8 --student-model openai: --student-reasoning-effort high --teacher-provider openai --teacher-model --teacher-reasoning-effort high --job-name demo --output-dir runs`, filling in the model names for your route. (inferred, check the README)",
  "Run `harness-zero build-sft --trials runs/demo --output sft.jsonl --reward-threshold 1.0`."
 ],
 "agent_prompt": "Using the repo metaevo-ai/harness-zero, run a reviewed rollout on the task IDs in <tasks-file> with the USPTO harness bank, then build an SFT dataset from runs/demo. Expected output: sft.jsonl containing only trials that met reward threshold 1.0. Verify that runs/demo contains trial results before you run build-sft.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "2 hours",
 "basis": "readme",
 "caveat": "The README names the USPTO route in the quickstart; other domains need their own harness_bank folder and task data.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.12 to 3.13 and uv installed",
  "Docker running, since rollouts run in local Docker sandboxes via Harbor",
  "API key for your model route (OpenAI, Azure AI Foundry, or OpenRouter) in a .env file copied from .env.example",
  "A Tinker key (TM_API_KEY) if you plan to run training"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "The .env file holds live model API keys, so keep it out of version control and do not paste keys into agent prompts."
  }
 ],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/metaevo-ai-harness-zero/generate-reviewed-agent-trajectories/",
 "md": "https://dedupedai.com/use-cases/metaevo-ai-harness-zero/generate-reviewed-agent-trajectories/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.",
 "api": "https://dedupedai.com/api/v1/usecases/metaevo-ai-harness-zero--generate-reviewed-agent-trajectories.json",
 "api_version": "v1"
}