{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/ask-a-coding-agent-for-one-coherent-increment-at-a-time",
  "id": "MHC-D-RESEARCH-0712",
  "version": "0.1.0",
  "title": "Ask a coding agent for one coherent increment at a time",
  "summary": "Autonomy works better when the unit of progress is small enough to verify.",
  "kind": "principle",
  "body": "Choose one ledger item or coherent slice, let the agent implement and test it, then persist the result before moving on. The slice can include multiple files, but it should end in an inspectable state. This reduces half-finished branches and makes failures easier to localize without forcing the human to micromanage line by line.",
  "limits": [
    "Do not fragment a change so aggressively that every increment is unusable or creates temporary architecture debt."
  ],
  "topics": [
    "union-ai-coding-harness-work"
  ],
  "intents": [],
  "source_ids": [
    "RS-953745C0ACB528FD"
  ],
  "evidence": [
    {
      "claim": "Anthropic's long-running harness improved coherence by asking the coding agent to make incremental progress on one feature rather than attempting the entire application at once.",
      "source_id": "RS-953745C0ACB528FD",
      "role": "supports",
      "note": "Some refactors are inherently cross-cutting; the increment still needs a coherent acceptance boundary.",
      "locator": "Choose a single feature and leave progress artifacts"
    }
  ],
  "use_when": [
    "An agent keeps touching many features, leaving partial implementations or declaring victory early."
  ],
  "avoid_when": [
    "Do not fragment a change so aggressively that every increment is unusable or creates temporary architecture debt."
  ],
  "example": "Instead of 'modernize the whole integration layer,' first complete one endpoint migration including tests, logging and documentation.",
  "check": "Each autonomous work interval ends with a coherent artifact, a verified status and a clear next item.",
  "sources": [
    {
      "id": "RS-953745C0ACB528FD",
      "title": "Effective harnesses for long-running agents",
      "url": "https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents"
    }
  ],
  "relations": [],
  "collections": [
    {
      "id": "RC-A76353E5E9A33FE5",
      "title": "Make coding agents work in inspectable increments",
      "url": "/collections/make-coding-agents-work-in-inspectable-increments"
    }
  ]
}