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.
Can you discuss a bit more of the architecture?
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.