# How do you handle governance for multi-agent crews?

**URL:** <https://community.crewai.com/t/how-do-you-handle-governance-for-multi-agent-crews/7939>\
**Category:** General\
**Tags:** agent\
**Created:** [October 20, 2026, 11:33am UTC](https://community.crewai.com/t/how-do-you-handle-governance-for-multi-agent-crews/7939 "2026-10-20T11:33:17Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Herve\_Kom](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/herve_kom/32/5337_2.png) [@Herve\_Kom](https://community.crewai.com/u/Herve_Kom)\
**Post date:** [October 20, 2026, 11:33am UTC](https://community.crewai.com/t/how-do-you-handle-governance-for-multi-agent-crews/7939/1 "2026-10-20T11:33:17Z")

</div>

With crews, one lead agent delegates to others, so accountability gets blurry fast. How do you track which human is responsible when agent A hands work to agent B?

One approach I’ve seen (in Sharkly.ai, disclosure: I work on it) records a _Triggered by_ field on every run that traces back up the chain to the person who started it.

For those running CrewAI in production: do you log delegation chains? Do you enforce human approval before a crew’s output is used?