AI Agents
AG-07Draft
Watch AI agents at work and pause one that goes wrong
How Leela would run itContinuous · while an agent is at work, with samples on the schedule the company sets
Proposed stepsThe requirement
What each AI agent says and does is sampled on a set schedule and checked against set warning signs, and a named person can pause an agent and review its work before it resumes.
- Before this work
- Access to the agents’ work records Agreed warning signs for each agent
- Applies
- Tell Leela about your company to see whether this applies.
- Status
- Setup needed
Tell Leela how you handle it today, or hand it over: see what’s next.
How Leela would run it · proposed steps
- LeelaSample each agent’s work on the set schedule and check it against the warning signs.Proposed step
- LeelaSend the named person anything that crosses a warning sign.Proposed step
- AI program ownerThe named person decides whether to pause an agent and when it resumes.Your team decides
What Leela keepsThe evidence this obligation leaves, as the work happens
Listed from the policy libraryContents
- 01Monitoring samplesDated samples with the warning signs checked and what was found
- 02Pause recordWho paused an agent, why, and when it resumed
Evidence
Monitoring samples
AI Agents §3.7
2
of 2 records
The steps are the library’s proposed workflow for this obligation: a description of the work, not a run. The records are its evidence in the library.