Rovo usually provides a single response.
Would it improve trust if it also explained:
Could this reduce hallucinations and increase confidence?
Hi @AGASTYA SHARMA,
Interesting question, but I would be careful about what you are asking for. An explanation of why other documents were not chosen would be generated by the model itself. It would sound convincing, but it can be just as made up as any other output.
What actually helps, from my point of view, is what Rovo already does: showing the sources it used so you can verify the answer yourself. In my experience, the bigger lever is on the content side. If Rovo picks the wrong Confluence page, that is usually a signal of duplicate, outdated, or conflicting content. Curating the knowledge base, archiving stale pages, and maintaining a single source of truth per topic do more for answer quality than any explanation feature.
Cheers, Martin
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.