Hi there, I'm working with agents and it can take quite a few minutes until you get the final result. How would you typically handle that in terms of UI/UX? The way I see it is that you could either use streaming (but then the UX is fully blocked until the result), or store intermediary results in db, show these intermediary results each time the user look back at that agent action page, and get a notification once completed to check that page. I wonder what best practice, good ideas would be for that?
I think a good option is just showing what step the agent is performing currently. For example if it's searching the internet the UI would say: "Agent is searching the web".
I probably wouldn't include intermediary results unless the user clicks something, for example if they want debugging for that step.
yeah that is the idea, but I'd like to understand how to do this on an API build perspective. Users might click away and get back to see the progress, so I guess a streaming API is out of questions. Which means that everytime a request is pending and/or the user comes back to the page, I would need to make API call to fetch the latest progresses