{
  "slug": "authority-graph",
  "title": "What can your AI agents do right now? Nobody can answer that.",
  "summary": "Nobody can list what their agents, tokens and app grants are allowed to do. Authority Opacity explained, and the signed authority graph that fixes it.",
  "lede": "Ask any organisation to list every action its agents, tokens and app grants can currently perform, and the honest answer is a shrug followed by three days of archaeology. Authority is scattered, tenant bound, and unverifiable by anyone outside the system that issued it. That gap has a name, and it has a shape.",
  "date": "2026-09-03",
  "reading_time": "17 min read",
  "category": "Agents",
  "tags": [
    "authority graph",
    "AI agent permissions",
    "non-human identity",
    "delegation chain",
    "agent governance",
    "revocation",
    "EU AI Act Article 14"
  ],
  "image": "https://cdn.twc.sh/images/igcache/Agent%20Authority%20Graph/1200_630/blog.jpg",
  "url": "/blog/authority-graph.html",
  "wordcount": 4451,
  "related": [
    "prove-agent-authorized",
    "delegation-tokens-explained",
    "kill-switch-design"
  ],
  "schema": "Article"
}