I tried to forge my own AI agent's audit log

Automated excerpt

One place an agent touches the outside world, and every action is checked before a model is even called. Agent-governance products — Workday's Agent Passport, Okta, Credo AI — all write logs. An agent undoing its own actions would be The core has zero dependencies.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.