# Asking the Activity Monitor why a user gave a thumbs down

**URL:** <https://community.solace.com/t/asking-the-activity-monitor-why-a-user-gave-a-thumbs-down/4987>\
**Category:** Solace Agent Mesh\
**Created:** [November 14, 2026, 4:00pm UTC](https://community.solace.com/t/asking-the-activity-monitor-why-a-user-gave-a-thumbs-down/4987 "2026-11-14T16:00:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Tamimi](https://yyz1.discourse-cdn.com/solace/user_avatar/community.solace.com/tamimi/32/2190_2.png) [@Tamimi](https://community.solace.com/u/Tamimi)\
**Post date:** [November 14, 2026, 4:00pm UTC](https://community.solace.com/t/asking-the-activity-monitor-why-a-user-gave-a-thumbs-down/4987/1 "2026-11-14T16:00:26Z")

</div>

Hello everyone,

Ask how your agents did this week and you get up and down counts and the negative ratio per agent and workflow, worst first. Ask for the negative comments on one agent and it lists the entries with their rating and comment.

The part I find most useful is explaining a single rating. On the Feedback History tab, Ask Activity Monitor sends one entry to the agent. It replays the chat session up to the rated response and tells you what went wrong. In the demo, a support agent gave a bad answer because its tracking lookup failed, and the explanation points right at it.

Everything respects RBAC. Someone with read\_feedback on certain agents sees only those, replaying a session also needs read\_trace, and a regular user sees only their own feedback.

Here’s the video:

[](https://www.youtube.com/watch?v=cwl-7p1htec)

How do you follow up on negative feedback today? Would this replace any of that for you? I’d love to hear in the thread.

If you want to try it yourself, you can [download Solace Agent Mesh](https://solace.com/products/agent-mesh/). Check it out on Github:

> **[GitHub - SolaceProducts/solace-agent-mesh: Platform for building and running AI agents across...](https://github.com/SolaceProducts/solace-agent-mesh)**
>
> Platform for building and running AI agents across the full lifecycle — build, test, deploy, monitor, improve. Hosts your agents, runs their tools, and coordinates them over an event mesh, with sessions, artifacts, auth, evaluators, and observability built in.