Skip to main content
The Feedback page surfaces what users actually thought of your agents’ replies: the like/dislike vote and any optional comment they left. It exists in two scopes:
  • Organization Feedback (sidebar entry at the org level): every agent in the org.
  • Agent Feedback (sidebar entry at the agent level, simply labeled “Feedback”): only the selected agent.
The two views share the same layout. The agent-scoped variant hides the Agent column.
Per-agent Feedback view with the same layout, scoped to a single agent
User Feedback page with distribution cards, dislike categories progress bars, and the recent feedback table

​
Period selector

A 7d / 30d / 90d selector in the header scopes the data on the page. A refresh button forces a re-fetch.

​
Distribution cards

Four KPI cards:

​
Dislike categories

When users dislike a reply, they can optionally tag the reason. The categories card shows progress bars for each: The card is hidden when there are no dislikes in the period.

​
Recent feedback table

The most recent feedback items, paginated with a See more button. Columns: On mobile the table collapses to a card layout with the same data.

​
When this page is empty

If no feedback has been collected, the page shows: “No feedback collected yet.” You can:
  • Make sure the agent’s UI exposes thumbs-up / thumbs-down; Chat and the Builder UI components do this by default.
  • Encourage users with prompts (“Was this helpful?”) inside the agent’s reply.

​
What to use this for

  • Quality triage. A surge in the Style/Tone category often points at a system prompt change. The Safety/Legal category should be reviewed daily; every entry is a candidate audit case.
  • Compare against LLM-as-judge. If your evaluation scores are high but the like rate is low, your criteria don’t align with what users actually value.
  • Per-agent diffing. Compare a known-good agent against a struggling one in the dislike category mix.

​
Where to go next

Read the per-conversation analysis

Cross-reference disliked conversations with the LLM-as-judge result.

Adoption

See like rate aggregated as part of the broader quality picture.