ok_orco

No I need to look into this!

Will take a look!

I haven't thought about that, but really want to dig in more now. Any places you recommend starting?

Pretty straightforward. Sources dump into a queue throughout the day, regex filters the obvious junk ("lol", "thanks", bot messages never hit the LLM), then everything gets batched overnight through Anthropic's Batch API for classification. Feedback gets clustered against existing pain points or creates new ones.

Most of the cost savings came from not sending stuff to the LLM that didn't need to go there, plus the batch API is half the price of real-time calls.