I built something like this and it was so rad, but oh my god was it ever expensive. I definitely advise using the 3.5-turbo model if you find the results acceptable, because it is 20x cheaper than the "guru level" genius of GPT-4. Aside from that hangup, automating Slack summaries is insanely useful as a manager.

Totally. And 3.5-turbo actually does a great job on this (and lots of other) tasks, in my experience, and is a fraction of the price. The entire endeavor cost us a few bucks of OpenAI tokens.