When I am attracted to look more closely at a topic here in Table Forums, this is what I see. (click to enlarge)
Certainly, this is not what you see in a Discourse interface. This is my personal Discourse Copilot. I wrote about the millions of AI copilots that would soon emerge. Many thought I was nuts - surely there might be a handful. But not millions. I still may be nuts, but this is not why. 
I built this Discourse Copilot some time ago. I use it especially when I discover a complex or lengthy conversation, and I want to follow it, inject some wisdom, or learn from it.
This solution exemplifies the power of Coda AI and almost every facet of a Coda solution. It uses a Pack to read and parse a Discourse conversation. It identifies influential participants, the key topic focus, and even attempts to see things that the participants may have overlooked. It collects data about the conversation and uses it to make inferences.
This is a tool that helps me understand people based on their interactions. Conversations contain valuable information, and this approach saves me a lot of time when I discover a topic that interests me. It gets me up to speed on the conversation by summarizing, organizing various perspectives, and visually displaying analytics.
This tool can be shaped for use with any conversational content. This example is for one Discourse community. I use it with seven Discourse communities and two other conversational data sources, including a customer survey system.
Imagine all these insights about all the Table Forum posts I’ve analyzed with this solution. Now picture them going to the “farm” to live out their days. The farm is my knowledge base. More on that another time.
You can get this copilot and shape it to be your own. It’s free.
I think you could also build something like this in Airtable.