{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "amap-ml-longhorizon-harness--split-roles-across-different-models",
 "repo": "AMAP-ML/LongHorizon-Harness",
 "repo_url": "https://github.com/AMAP-ML/LongHorizon-Harness",
 "repo_slug": "amap-ml-longhorizon-harness",
 "title": "Split planning, execution, and auditing across models",
 "page_title": "How to split planning, execution, and auditing across models with Long Horizon Harness",
 "summary": "Assign a different model or backend to the Manager, Executor, and Auditor of one task.",
 "who": "A team that wants to balance quality, speed, and cost on a long task and does not want one model doing all three jobs.",
 "problem": "One model handling planning, acting, and checking can be costly, and the same model may approve its own work without a real check.",
 "outcome": "A task where each loop role runs on the model or backend chosen for it, with the Auditor checking the actual files and logs.",
 "steps": [
  "Complete the Installation steps and confirm at least two agent runtimes are on PATH.",
  "Run `lh-harness web` and open the Dashboard.",
  "For each role, pick the backend and model: Manager for planning, Executor for actions, and Auditor for checks.",
  "Start the task and watch which round the Auditor accepts or rejects.",
  "Compare the final verified state with the goal to confirm the result."
 ],
 "agent_prompt": "Use the LongHorizon-Harness repo at <repo path> to run a task for <goal> with a different model assigned to the Manager, Executor, and Auditor. Expected output: a verified result and a list of accepted checkpoints. Verify that the Auditor inspected the real files or logs rather than relying on the Executor's claim.",
 "agents": [
  "claude-code",
  "codex"
 ],
 "difficulty": "Intermediate",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "Per-role model and backend selection is shown in the README for the Web workbench, but the full list of supported models per backend is not visible in the truncated text.",
 "category": "Work and operations",
 "tags": [
  "Work and operations"
 ],
 "lang": "python",
 "requirements": [
  "uv, or pip with Python 3.10 or later",
  "One agent runtime on PATH, such as codex, claude, or opencode",
  "A goal for the agent and a project folder to work in"
 ],
 "risk": "sensitive",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/amap-ml-longhorizon-harness/split-roles-across-different-models/",
 "md": "https://dedupedai.com/use-cases/amap-ml-longhorizon-harness/split-roles-across-different-models/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/amap-ml-longhorizon-harness--split-roles-across-different-models.json",
 "api_version": "v1"
}