mambrogi

Yea in my mind citations in this case would be the agent's reasoning and action trace. Like "I looked at all expenses in February and summed them."

But this adds another layer of complexity figuring out how to properly generate this user facing trace. This is something I like from PromptQL's approach.

In practice you'd probably try to limit to just a few key tables. Probably limit columns the model is controlling as well and provide a lot of detail about what each captures. I think this would help a lot. But overall I don't disagree.

I was able to try the app out, really love the concept. Often find it easier to sneak in audio throughout the day than reading. Are the 'podcasts' designed to be more of a condensed version of the original article in the same tense? Or are they more of a narrative like Founders podcast or something?