13.02
What an agent may do without asking
Set unattended authority per action from reversibility and reliability, record it in an authority table, enforce tool allowlists, run the agent on scoped credentials, and treat money as irreversible with billing spend caps.
- Defining AI Guardrails and Agent Security
- 16 min
- Pro
Who's hiring for this skill
8 companies have live AI-PM roles that ask for skills taught in this lesson.
- Writer
- Coursera
- Decagon
- Datadog
- Snowflake
- Stripe
- Gusto
- Box
This subchapter is part of the paid course.
Its video, its written lesson, its exercise and its grading are all included on any plan. The free subchapters stay free either way.