{
  "slug": "human-agent-delegation",
  "title": "Human-agent delegation: who authorised what your AI agents do",
  "summary": "Agents act. No existing identity mechanism records which human authorised the action. A guide to delegation chains, authority graphs and agent accountability.",
  "lede": "An agent takes an action. Something goes wrong. Someone asks who authorised it, and the answer turns out to be a service account, a token issued eight months ago, and a prompt nobody kept. This page is about the artifact that should have existed instead, why none of the current identity stack produces it, and what a delegation that survives an incident review actually looks like.",
  "date": "2026-10-02",
  "reading_time": "21 min read",
  "category": "Pillar",
  "tags": [
    "human-agent delegation",
    "AI agent authorisation",
    "delegation chain",
    "agent identity",
    "authority graph",
    "human in the loop",
    "agent accountability"
  ],
  "image": "https://cdn.twc.sh/images/igcache/Human%20Agent%20Delegation/1200_630/blog.jpg",
  "url": "/blog/human-agent-delegation.html",
  "wordcount": 5441,
  "related": [
    "proof-of-human-intent",
    "authority-graph",
    "approval-theater"
  ],
  "schema": "Article"
}