{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/turn-repeated-browser-work-into-persistent-programs",
  "id": "MHC-D-RESEARCH-1171",
  "version": "0.1.0",
  "title": "Turn repeated browser work into persistent programs",
  "summary": "Use the browser to learn the path; use code to stop relearning it every time.",
  "kind": "heuristic",
  "body": "After a browser interaction pattern becomes stable, encode the repeatable mechanics in a script or reusable skill. Let the live browser remain the state and feedback surface for checking whether the program still matches reality. Fall back to exploratory interaction when the site changes.",
  "limits": [
    "Do not freeze brittle selectors or bypass site rules. Persistent automation still needs authorization, monitoring and recovery."
  ],
  "topics": [
    "union-ai-runtime-verification-2026"
  ],
  "intents": [],
  "source_ids": [
    "RS-05CEF906EF829016"
  ],
  "evidence": [
    {
      "claim": "Repeated browser interactions can be moved into persistent programs or reusable website skills while live browser state remains the feedback surface.",
      "source_id": "RS-05CEF906EF829016",
      "role": "supports",
      "note": "Persistent automation becomes stale when websites or permissions change; it still needs error handling, observation and a fallback to fresh discovery.",
      "locator": "8:12, turn browser actions into persistent programs, within a harness that continues until a verifiable goal is reached"
    }
  ],
  "use_when": [
    "A browser agent repeatedly rediscovers the same navigation and action sequence on a site."
  ],
  "avoid_when": [
    "Do not freeze brittle selectors or bypass site rules. Persistent automation still needs authorization, monitoring and recovery."
  ],
  "example": "An agent first learns how to export a monthly report through the UI; after repeated success, a reusable automation handles the known sequence while the browser verifies the resulting state.",
  "check": "Repeated work uses a versioned, testable action path and still detects when the live site no longer matches it.",
  "sources": [
    {
      "id": "RS-05CEF906EF829016",
      "title": "Codex, Behind the Harness",
      "url": "https://ai.engineer/talks/shRR1e2HXMk-codex-behind-harness"
    }
  ],
  "relations": [],
  "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"
    }
  ]
}