12.02
What an agent may do without asking
You set what an agent may do unattended from reversibility times measured reliability, write that as a per-action authority table, give it a non-human identity with scoped expiring credentials, and treat money as the irreversible action with spend limits enforced at the payment layer.
- 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.