[RCA + LLM] Allow user to update LLM output in place and re-run LLM analysis

elastic / kibana

Your window into the Elastic Stack

https://www.elastic.co/products/kibana

Other

19.67k stars 8.23k forks source link

[RCA + LLM] Allow user to update LLM output in place and re-run LLM analysis #197859

Open jasonrhodes opened 4 weeks ago

jasonrhodes commented 4 weeks ago

The LLM produces output (hypotheses, a final report, significant events, etc) after it has completed its analysis. We should allow the user to interact with some portion of the LLM output (the hypotheses, likely) and use the edited input to re-run the analysis, similar to how the AI assistant allows this in chat.

We will need more detail here on how this is intended to work.

elasticmachine commented 4 weeks ago

Pinging @elastic/obs-ux-management-team (Team:obs-ux-management)