I committed to Perplexity so I can have access to most models I care about easily, deep research, and better online search. I’m happy with Perplexity, but I’ve been Kagi curious for years and now I’m even less sure how I’d approach using it.
I happen to prefer that and just rely on Claude to run its own searches via API, but I haven't used Perplexity so can't compare them directly. Hope that's helpful!
Assuming you default with Kagi, but switch to Claude (API? Raycast?) for search if you don’t like the results you get?
Perplexity I’ve found incredibly powerful for search as it’s fast, and I love being able to toggle “Social” as a source quickly before sending an inquiry off - in case I want opinions vs sources.
That said, I have found it on occasion being lackluster a handful of times on the first go, so I have to manually switch the model from the default “Best” mode (which selects the best model for the task) - to specifically Gemini, o3 etc. to get a better result.
Pretty handy. You can also make your assistants use the same custom 'lenses' you do to constrain their searches.
For example, one of their default lenses is "Academic". It searches research institutions/scientific journals/universities/etc. So as an example, if I search "ulcer risk of ibuprofen":
The "Academic" lens returns the NIH with "Research summaries -- Preventing peptic ulcers"[0] and ScienceDirect with a paper on "The gastrointestinal effects of nonselective NSAIDs and COX-2-selective inhibitors"[1].
Searching without the lens, I get Healthline's "Ibuprofen and Ulcers: Why They Happen and How To Avoid Them"[2] and Medical News Today's "Ibuprofen ulcers: Effects, symptoms, causes, and more"[3].
You can apply these lenses to searches the AI assistant performs separately from the prompts/context/etc. So, for instance, I can set up an "assistant" based on Claude called "Research" restricted to the "Academic" lens. When I ask that assistant questions and it performs a web search, only results from the academic lens (research institutes, universities, etc) will be returned to the AI.
You could do similar with, e.g., setting up an assistant for "Coding with Python" and creating a lens that's restricted to the Python documentation, one for "Local Knowledge" that's restricted to sites from your region, "Recent Developments" that only considers sites published in a certain timeframe, "eBooks" that only returns epub results, etc.
Your prompt/etc is configured separately as part of the "assistant" you're using. So you could have a research assistant with a prompt that asks it to approach the problem step-by-step and evaluate the veracity of the sources, a coding assistant whose prompt includes the language/framework, etc. But there's nothing stopping you hooking your "research assistant" up to your "Coding with Python" lens.
[0] https://www.ncbi.nlm.nih.gov/books/NBK310269/ [1] https://www.sciencedirect.com/science/article/abs/pii/S00490... [2] https://www.healthline.com/health/ibuprofen-ulcer [3] https://www.medicalnewstoday.com/articles/ibuprofen-ulcers