{
  "abstract": "A practical operating model for meaningful agent work: begin with a job, encode the work, bound the assignment, supervise through evidence, measure results, and expand autonomy only when repeatable proof earns a larger trust envelope.",
  "author": {
    "email": "tony@malott.ai",
    "email_url": "mailto:tony@malott.ai",
    "id": "person:tony-malott",
    "name": "Tony Malott",
    "resume_url": "https://malott.ai/resume/",
    "url": "https://malott.ai/"
  },
  "card": {
    "kicker": "Operating model",
    "orientation": "A dependable agent is built by its management system, not by discovering a perfect prompt.",
    "visual_motif": "worker-contract"
  },
  "collections": [
    {
      "id": "collection:from-prompts-to-governed-work",
      "position": 2,
      "title": "From prompts to governed work"
    }
  ],
  "dates": {
    "created": "2026-07-18",
    "updated": "2026-07-19"
  },
  "featured": true,
  "format": {
    "depth": "Applied deep read",
    "interaction": "Static article with operating-model structure",
    "label": "Teaching architecture",
    "reading_time": "15 min"
  },
  "graph_order": 2,
  "id": "artifact:stop-prompting-agents-start-managing-workers",
  "lifecycle": {
    "merge_authority": "granted-for-pr-8",
    "owner_review": "accepted-information-design-lock-v01",
    "state": "MERGE_READY"
  },
  "migration": {
    "admission_id": "admission:stop-prompting-agents-start-managing-workers",
    "content_fidelity": "Exact predecessor article source preserved; presentation, metadata, relationships, and generated outputs redesigned natively.",
    "disposition": "redesign",
    "source_locators": [
      "Issue #190",
      "PR #191",
      "docs/publication/issue-190/ARTICLE.md"
    ],
    "source_repository": "pinklon/pinklon-shareplane-next"
  },
  "presentation_status": "locked",
  "provenance": {
    "ai_assistance": {
      "role": "platform-native metadata, relationship, rendering, and migration implementation",
      "used": true
    },
    "boundary": "The employee analogy governs work design, not personhood or accountability. Accountability remains with the people and systems authorizing the work.",
    "posture": "Exact predecessor article source preserved with platform-native metadata, cards, relationships, and generated projections.",
    "sources": [
      {
        "id": "source:shareplane-next-issue-190",
        "locator": "https://github.com/pinklon/pinklon-shareplane-next/issues/190",
        "role": "Defines the canonical thesis, public-safe boundary, publication model, and required teaching components.",
        "title": "Predecessor teaching-work authority Issue #190",
        "type": "semantic-authority"
      },
      {
        "id": "source:shareplane-next-pr-191",
        "locator": "https://github.com/pinklon/pinklon-shareplane-next/pull/191",
        "role": "Preserves the exact public article source used by this pilot.",
        "title": "Predecessor locked article package PR #191",
        "type": "source-lineage"
      },
      {
        "id": "source:shareplane-platform-issue-7",
        "locator": "https://github.com/pinklon/shareplane-platform/issues/7",
        "role": "Selects the teaching work for the pilot and authorizes platform-native redesign.",
        "title": "SharePlane Platform corpus design authority",
        "type": "governing-issue"
      }
    ]
  },
  "public": true,
  "public_safe_status": "reviewed",
  "relationships": [
    {
      "label": "Authored by Tony Malott",
      "target_id": "person:tony-malott",
      "type": "authored_by"
    },
    {
      "label": "Governed by corpus presentation Issue #7",
      "target_id": "issue:shareplane-platform:7",
      "type": "governed_by"
    },
    {
      "explanation": "The memoir supplies the personal failures and systems insight behind explicit context, authority, validation, receipts, and the shift from magical agents to governed workers.",
      "label": "Why the worker model became necessary",
      "reader_group": "foundations",
      "target_id": "artifact:i-was-summoning-ghosts-until-i-learned-to-build-the-machine",
      "type": "foundation"
    },
    {
      "explanation": "Once bounded agent workers can execute faster, the constraint moves upstream to human specification, supervision, validation, integration, memory, and closure.",
      "label": "What changes after the worker model succeeds",
      "reader_group": "continue",
      "target_id": "artifact:the-agents-are-not-the-bottleneck-you-are",
      "type": "continuation"
    }
  ],
  "schema_version": "2.0.0",
  "semantic_status": "locked",
  "slug": "stop-prompting-agents-start-managing-workers",
  "source": {
    "content_status": "canonical-full",
    "format": "markdown",
    "path": "content/artifacts/stop-prompting-agents-start-managing-workers/source.md",
    "predecessor_sha": "c810d095fae997c0a384e0c47b21850f339db5f8"
  },
  "subtitle": "Manage the work like an employee. Control the system like powerful machinery.",
  "thesis": "Agent workers become dependable only when organizations stop treating them as intelligent prompt boxes and start managing their work through explicit roles, encoded procedures, bounded authority, evidence, measurement, and earned autonomy.",
  "title": "Stop Prompting Agents. Start Managing Workers.",
  "topics": [
    "agent-workers",
    "operating-contracts",
    "earned-autonomy",
    "evidence",
    "management-systems"
  ],
  "type": "teaching-architecture"
}