{
  "id": "artifact:the-agents-were-never-the-bottleneck",
  "slug": "the-agents-were-never-the-bottleneck",
  "title": "The Agents Were Never the Bottleneck",
  "thesis": "Capable agents became useful when Tony engineered the repositories, access, tools, authority, validation, evidence, and completion paths that made bounded work operational.",
  "abstract": "A first-person systems essay about the engineered workbench surrounding useful agent execution, why learning the mechanics made trustworthy delegation possible, and how governable execution returned senior human attention to architecture, judgment, sequencing, taste, and risk.",
  "topics": [
    "agentic-systems",
    "operational-readiness",
    "software-delivery",
    "governance",
    "fault-isolation"
  ],
  "date": "2026-07-20",
  "dateLabel": "Source dated",
  "published": false,
  "publicationState": "PREVIEW_READY",
  "updated": "2026-07-20",
  "sourceDates": {
    "created": "2026-07-20",
    "updated": "2026-07-20"
  },
  "kind": "Systems Essay",
  "sourceFamily": "SharePlane Platform",
  "href": "artifacts/the-agents-were-never-the-bottleneck/index.html",
  "contextHref": "records/the-agents-were-never-the-bottleneck/context.txt",
  "recordHref": "records/the-agents-were-never-the-bottleneck/work.json",
  "receiptHref": "records/the-agents-were-never-the-bottleneck/receipt.json",
  "packageHref": "downloads/works/the-agents-were-never-the-bottleneck.zip",
  "canonicalUrl": "https://shareplane.malott.ai/artifacts/the-agents-were-never-the-bottleneck/",
  "sources": [
    {
      "id": "source:shareplane-platform-issue-44",
      "type": "governing-issue",
      "title": "SharePlane Platform Issue #44",
      "locator": "https://github.com/pinklon/shareplane-platform/issues/44",
      "role": "Governs the thesis, semantic lock, canonical article, creative lock, rendering lane, and owner-review boundary",
      "description": "Owner authority for the workbench thesis, its causal chain, non-claims, evidence posture, and three presentation candidates.",
      "publiclyExposed": true
    },
    {
      "id": "source:shareplane-platform-issue-18",
      "type": "semantic-boundary",
      "title": "SharePlane Platform Issue #18",
      "locator": "https://github.com/pinklon/shareplane-platform/issues/18",
      "role": "Defines the adjacent thesis that each completed agent job should leave the workbench smarter",
      "description": "Used to preserve the boundary between constructing the workbench and improving it through later completed work.",
      "publiclyExposed": true
    },
    {
      "id": "source:github-about-pull-requests",
      "type": "official-technical-documentation",
      "title": "About pull requests",
      "locator": "https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests",
      "role": "Supports the limited claim that pull requests expose proposals, discussion, review, commit history, and checks before merge",
      "description": "Official GitHub mechanics; it does not establish that GitHub alone creates governance or a complete agent workbench.",
      "publiclyExposed": true
    },
    {
      "id": "source:github-about-status-checks",
      "type": "official-technical-documentation",
      "title": "About status checks",
      "locator": "https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/collaborating-on-repositories-with-code-quality-features/about-status-checks",
      "role": "Supports the limited claim that checks expose pending, passing, and failing CI state for commits and pull requests",
      "description": "Passing checks prove only the conditions encoded by those checks and do not establish semantic correctness.",
      "publiclyExposed": true
    },
    {
      "id": "source:anthropic-effective-tools",
      "type": "official-engineering-guidance",
      "title": "Writing effective tools for agents — with agents",
      "locator": "https://www.anthropic.com/engineering/writing-tools-for-agents",
      "role": "Supports the limited claim that tool selection, boundaries, returned context, descriptions, and evaluations affect agent effectiveness",
      "description": "Vendor engineering guidance, not a universal controlled study or guarantee of reliable autonomy.",
      "publiclyExposed": true
    },
    {
      "id": "source:anthropic-agent-evals",
      "type": "official-engineering-guidance",
      "title": "Demystifying evals for AI agents",
      "locator": "https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents",
      "role": "Supports explicit success criteria and outcome evaluation across multi-turn tool use and state changes",
      "description": "Evaluation makes behavior visible; it does not guarantee correctness, safety, or fitness.",
      "publiclyExposed": true
    },
    {
      "id": "source:openai-workspace-agents",
      "type": "official-product-documentation",
      "title": "ChatGPT Workspace Agents for Enterprise and Business",
      "locator": "https://help.openai.com/en/articles/20001143",
      "role": "Supports the limited claim that production agent configuration models tools, authentication, permissions, least privilege, audience limits, and audits explicitly",
      "description": "Product documentation shows explicit controls; it is not independent proof that those controls guarantee reliable or safe operation.",
      "publiclyExposed": true
    }
  ],
  "posture": "owner-originated-experience-backed-architecture-thesis-with-ai-assisted-structure-research-rendering-and-validation",
  "media": [],
  "schema": "shareplane.portable-work.v1",
  "author": {
    "name": "Tony Malott",
    "url": "https://malott.ai/"
  },
  "content": {
    "mediaType": "text/plain",
    "path": "records/the-agents-were-never-the-bottleneck/context.txt",
    "sha256": "0786194a3afb3a8f75e2d418c476307b09af7c47e62d522f8cc51452544f0383",
    "complete": true,
    "extraction": "Native presentation reading order; scripts, styles, and platform chrome excluded."
  },
  "relationships": [
    {
      "source": "artifact:the-agents-were-never-the-bottleneck",
      "target": "artifact:the-human-is-the-bottleneck",
      "type": "companion",
      "group": "companions",
      "label": "Move from human constraint to operational substrate",
      "explanation": "The companion essay examines imagination, judgment, execution discipline, and restraint as human constraints; this essay locates the prerequisite for delegated execution in the engineered workbench around the agent."
    },
    {
      "source": "artifact:the-agents-were-never-the-bottleneck",
      "target": "artifact:stop-prompting-agents-start-managing-workers",
      "type": "application",
      "group": "applications",
      "label": "Apply the workbench through bounded worker management",
      "explanation": "The teaching artifact turns the workbench into an operating model of explicit roles, bounded assignments, evidence, validation, and approval gates without surrendering human accountability."
    }
  ],
  "representations": {
    "html": "artifacts/the-agents-were-never-the-bottleneck/index.html",
    "text": "records/the-agents-were-never-the-bottleneck/context.txt",
    "json": "records/the-agents-were-never-the-bottleneck/work.json",
    "package": "downloads/works/the-agents-were-never-the-bottleneck.zip"
  }
}