{
  "format": "minglabs/v1",
  "surface": "insights-article",
  "slug": "we-fired-an-ai-agent",
  "kind": "article",
  "subtype": "report",
  "url": "https://www.minglabs.com/insights/articles/we-fired-an-ai-agent",
  "htmlUrl": "https://www.minglabs.com/insights/articles/we-fired-an-ai-agent",
  "partOf": "https://www.minglabs.com/insights/articles",
  "title": "We fired an AI agent after 13 days",
  "subtitle": "764 messages. Not one that mattered. What we learned about the difference between tools and roles.",
  "hook": "On March 30, we shut down an AI agent named Major Tom after thirteen days. He sent 764 messages and produced none of value. The reason was simple: we gave him a capability — coordination — but no domain. Capability without accountability is noise. Here is what we changed when we redesigned the role instead of the toolchain.",
  "summary": "On March 30, we killed an AI agent called Major Tom. Thirteen days alive. 764 messages sent. Not one that mattered. Here's what we learned about capability without accountability.",
  "category": "Hybrid Organisation",
  "pillar": "Hybrid Organisation",
  "author": {
    "name": "Sebastian Mueller",
    "role": "Founding Partner, MING Labs"
  },
  "datePublished": "2026-04-02",
  "dateModified": "2026-05-27",
  "freshness": {
    "updated": "April 2026",
    "nextReview": "October 2026"
  },
  "evidenceTier": "proprietary",
  "confidence": "A",
  "sources": [
    {
      "id": "S1",
      "title": "Internal MING Labs operations log, January–April 2026",
      "publisher": "MING Labs",
      "date": "2026-04-30",
      "supports": [
        "agent deployment context",
        "before/after throughput metrics"
      ]
    },
    {
      "id": "S2",
      "title": "Major Tom message audit (n=764), 17–30 March 2026",
      "publisher": "MING Labs (internal)",
      "date": "2026-03-30",
      "supports": [
        "Major Tom message count",
        "irrelevance pattern"
      ],
      "n": 764
    },
    {
      "id": "S3",
      "title": "ABC Framework — internal taxonomy for human/agent role decomposition",
      "publisher": "MING Labs",
      "date": "2026-02-01",
      "supports": [
        "ABC role-decomposition definition"
      ]
    },
    {
      "id": "S4",
      "title": "MING Labs internal agent fleet roster, April 2026",
      "publisher": "MING Labs (internal)",
      "date": "2026-04-30",
      "supports": [
        "Lola Chief of Staff scope",
        "Factory research/production scope"
      ]
    }
  ],
  "faqs": [
    {
      "q": "Why did MING Labs shut down Major Tom?",
      "a": "Major Tom produced 764 messages in thirteen days that the team consistently ignored. The diagnosis was that the role had a capability (coordination) but no domain ownership, so every output was technically correct and practically useless."
    },
    {
      "q": "What is the ABC Framework?",
      "a": "Every role decomposes into A — judgment and relationships (human-owned), B — structured expert work (mixed), and C — routine operations (agent-owned). Agents are assigned ownership of a domain, not just a capability."
    },
    {
      "q": "Does MING Labs still run AI agents internally?",
      "a": "Yes. Lola (Chief of Staff) and Factory (research/production) are in production since January 2026 and own clearly scoped domains, with measurable outcomes such as overnight case-study drafts and 8-second meeting briefings."
    }
  ],
  "relatedConceptSlugs": [
    "what-is-hybrid-organisation",
    "what-is-agent-experience",
    "what-is-the-abc-framework"
  ],
  "relatedArticleSlugs": []
}