← All sections
§14

The Agent Card (spec)

The single document that defines an agent. Templated so every agent in the portfolio is described the same way.

Minimum sections:

  1. Identity — agent name, ID, owner, department, version.
  2. Purpose — the workflow it serves, the KPI it moves.
  3. Scope — what it will do and what it will explicitly not do.
  4. Risk tier + risk drivers — Low/Medium/High; PII / consequential / autonomous tags.
  5. Inputs / data sources — every system it reads from; data classification per source.
  6. Outputs / tool calls — every API or system it writes to; permission scope per call.
  7. Autonomy level — Assistive / Validated / Autonomous, with explicit thresholds for any autonomy.
  8. Identity & credentials — service principal / agent identity in the IdP; rotated how / when.
  9. HITL gates — where humans must approve, by rule.
  10. Failure modes & worst-case — what is the worst action this agent could take, and is that acceptable?
  11. Monitoring + alerts — what we watch, what triggers a page.
  12. Eval criteria — how we know it works; pre-prod test set.
  13. Retirement criteria — what would cause us to retire it.