This is my favorite thing about Kagi; you can do both. If you just append a question mark, it'll run the search through a simple LLM and give you those results (with citations) right before standard search. From there, you can proceed into a more sophisticated frontier model if that's more effective.
"Search" can mean a lot of things. Sometimes I just want a website but can't remember the URL (traditional); other times I want an answer (LLMs); and other times, I want a bunch of resources to learn more (search+LLMs).
I've found Kagi's Universal Summarizer useful for:
- Long reads when I just want to know the conclusion
- Reading terms of services that I would otherwise have blindly accepted
- Summarizing key requirements in large tender documents prior to bidding on work
As for summaries in general, FastGPT is so useful I apply it to most of my searches.
Especially if I'm looking for a small fact buried in the first results.
