For auditors

Audit AI agents in days, not months.

Fetch a signed Evidence Pack™ from a URL, verify it offline with public keys, and map it straight to your own control framework — without scheduling a single interview with the vendor.

Chain of authority

Demo data

You learn: Where this agent's authority comes from, at which hop it holds or stops, and what is sealed. You can: Walk the chain hop by hop.

Expected outcome
  • Decision Require approval
How this widget is built
Demonstrates
Decision feed
Components
  • Principal
  • Delegated grant (actions, purpose, limit, jurisdiction, expiry)
  • Agent grant
  • Policy decision point (kye_decide)
  • Decision record and evidence pack
Flow
Principal → delegation → agent → action → allow / deny / approval → sealed decision record and evidence pack. Architecture diagram
Used on
  • /examples/: On the examples page, with the rest of its scenario.
Full reference index — every page tagged for auditor (345) ↓

Derived from the graph

345 pages tagged for auditor.

This page is a derived view over internal. Adding or retagging a page rebuilds this landing on the next CI run — no hand-curated list to maintain.

Evaluate

Evaluate — 298 pages

Decide whether KYE Protocol™ is the right rail for the problem in front of you.

Operate

Operate — 4 pages

Run KYE Protocol™ in production — deploy, govern, observe, recover.

Audit

Audit — 7 pages

Audit a KYE™-governed system in days, not months — signed evidence, public-key verifiable.

Learn

Learn — 8 pages

Learn the rail — glossary, frameworks, frameworks-explained.

Reference

Reference — 28 pages

Look up the canonical definition — schemas, dictionaries, ID format.

Ready to evaluate KYE Protocol™?

Start in shadow mode. We’ll deliver your first Evidence Pack™ in 4–8 weeks.

Canonical KYE™ surfaces referenced on this page: KYE™ Production Action Authority™ · Systemic Authority Risk™.