{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/give-computer-use-tasks-a-start-state-and-success-check",
  "id": "MHC-D-RESEARCH-1175",
  "version": "0.1.0",
  "title": "Give computer-use tasks a start state and success check",
  "summary": "A screenshot is not a test case until you know where the task starts and what state counts as success.",
  "kind": "protocol",
  "body": "Specify the initial environment, relevant files or accounts, and a success predicate before the run. Reset to that state for comparable trials. Prefer checking the resulting system state over inferring success from the agent's final message.",
  "limits": [
    "Clean start states can underrepresent messy production environments. Add controlled variants after the base task is reliable."
  ],
  "topics": [
    "union-ai-runtime-verification-2026"
  ],
  "intents": [],
  "source_ids": [
    "RS-273F6FA5C48C6C0B"
  ],
  "evidence": [
    {
      "claim": "Computer-use evaluations are easier to interpret when each task defines a known initial environment and a verifiable success condition.",
      "source_id": "RS-273F6FA5C48C6C0B",
      "role": "supports",
      "note": "A clean initial state improves reproducibility but can be easier than messy production desktops; representative variants should be added after the basic task is stable.",
      "locator": "6:34-9:34, give each GUI task an initial state and success check, then test how the computer tool changes the result"
    }
  ],
  "use_when": [
    "A GUI or computer-use agent is evaluated on tasks whose initial desktop state or completion condition is ambiguous."
  ],
  "avoid_when": [
    "Clean start states can underrepresent messy production environments. Add controlled variants after the base task is reliable."
  ],
  "example": "For a spreadsheet task, seed the same workbook and mark success by the requested values and formulas in the saved file, not by the agent saying 'done.'",
  "check": "Another evaluator can reset the task and determine pass or fail from the resulting state without reading the agent's self-report.",
  "steps": [
    "Define the starting desktop or application state.",
    "Seed the files, account data or document needed for the task.",
    "Define a success predicate on resulting state.",
    "Reset the environment before the next comparable trial."
  ],
  "sources": [
    {
      "id": "RS-273F6FA5C48C6C0B",
      "title": "Computer-Use 2.0: Agents Just Got Multi-Cursor",
      "url": "https://ai.engineer/talks/ZSQb5fzRFPw-computer-use-2-0-agents-just-got"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-1175",
      "to": "MHC-D-RESEARCH-0722",
      "type": "useful_with",
      "url": "/knowledge/run-ai-evals-from-a-clean-starting-state"
    }
  ],
  "collections": [
    {
      "id": "RC-ACD6385FB70207D3",
      "title": "Operate AI agents as systems you can replay, verify and constrain",
      "url": "/collections/operate-ai-agents-as-systems-you-can-replay-verify-and-constrain"
    }
  ]
}