Not op, but Kagi user. Also have perplexity but usually use kagi.
I would say:
1) The UI. You’re still performing normal searches in Kagi. But if you hit q, or end your query with a question mark, you get an llm synthesized answer at the top, but can still browse and click through the normal search results.
2) Kagi has personalization, ie you uprank/downrank/block domains, so the synthesized llm answer should usually be better because it has your personalized search as input.
In addition to all that's been written above, you can configure personal filters, so that (for example) you never ever see a pinterest page in your search results. Things like that are IMO killer features today.
I would say: 1) The UI. You’re still performing normal searches in Kagi. But if you hit q, or end your query with a question mark, you get an llm synthesized answer at the top, but can still browse and click through the normal search results.
2) Kagi has personalization, ie you uprank/downrank/block domains, so the synthesized llm answer should usually be better because it has your personalized search as input.