Skip to main content
The pages before this one are about building an agent: giving it data, encoding your context, deploying it, and watching how it performs. This section is about the other side of that deployment — what your end users actually do once the agent is in front of them. An analytics agent is not a one-shot question box. Users ask a question, get a chart, and then want to keep it: tell you whether the answer was good, send it to a colleague, save it for next week, and eventually assemble the good ones into something that looks like a dashboard they built themselves. Upsolve ships that whole loop, and each part of it feeds back into the observability surfaces you use to improve the agent.
The end-user chat view, showing a question asked in natural language, the chart the agent produced, and the feedback, share and favorite actions beneath it

​
The loop

Giving Feedback

Thumbs up and thumbs down on any answer, with a structured feedback form when something was wrong.

Sharing an Analysis

Turn one answer, or a whole conversation, into a link anyone can open.

Favorites

Save a chart or query, come back to it later, and pick the conversation back up where it left off.

Canvas

Arrange favorites into a live or snapshot board and share it privately, org-wide, or publicly.

​
Where these features are available

Everything in this section works in the three places an agent runs:
  • Agent Studio — while you’re building and testing, so you can try the end-user experience yourself before shipping it.
  • Embedded in your product — the embedded agent exposes the same feedback, sharing, favorites and canvas surfaces to your users, scoped to their tenant.
  • Shared links — a shared analysis or a public canvas opens for someone who has no Upsolve account at all.
Favorites and Canvas are currently marked Beta in the product. They are functional and in production use, but the surface is still moving — expect refinements.

​
Why it matters for the builder

Each of these surfaces is also a signal:
  • Feedback lands in the Feedback column of Chat History, next to the automated evaluations, so you can compare what users think with what the evaluators think.
  • A favorited chart is a user telling you which answers are worth keeping — good raw material for a Golden Chart.
  • A conversation that gets shared or forked repeatedly is a question your agent should be answering well every time.