Debate: do you feed GPT your raw data or summarize it first?

I spent 3 days testing two ways of using AI to analyze customer feedback for a small ecommerce site. One side: feed it the raw CSV with messy comments and let the AI figure out patterns. Other side: clean and summarize the data yourself first, then ask specific questions. I tried the raw method and got some wild insights I never would have found, but also a bunch of noise. The summarised version was cleaner but missed some subtle complaints about shipping times. Curious what others do here, especially if you've tested both. Which approach gave you better results?

2 comments

2 Comments

thea7041mo ago

That "purple giraffe problem" story is painfully relatable, I feel your pain on that one.

samthompson1mo ago

Huh, that's an interesting experiment but I think you might be looking at it wrong. The real trick isn't choosing one or the other, it's doing a rough pass first to clean obvious junk like blank cells or test entries, then feeding that trimmed version to the AI raw. I tried dumping a full spreadsheet of support tickets once and got back some wild nonsense about a "purple giraffe problem" that turned out to be a formatting error in one column. Now I take 10 minutes to strip out bot comments and fix obvious misspellings, and the AI does way better finding things like the shipping complaints you mentioned.