Kagi + Wolfram
Building a search engine is hard. Delivering accurate and reliable search results requires processing vast amounts of data, understanding complex queries, and constantly evolving to meet user expectations. In an era where AI-generated content is becoming more prevalent, ensuring the trustworthiness of information provided by the search engine is more important than ever.
At Kagi, we are committed to providing our users with the most accurate and dependable search experience possible. We adhere to a philosophy of using AI to enhance, rather than create, search experience, and only when explicitly requested by the user. To ensure result quality, we automatically downrank pages with advertising and tracking, which are often associated with low-quality or machine-generated content. Our personalization features allow users to customize their search feed according to their preferences. Furthermore, we strive to promote authentic content from personal blogs and websites through our “Small Web” initiative, which aims to increase the visibility of genuine, high-quality content.
To further enhance our search capabilities and address the issue of potentially misleading AI-generated answers, we have partnered with Wolfram|Alpha, a well-respected computational knowledge engine. By integrating Wolfram Alpha’s extensive knowledge base and robust algorithms into Kagi’s search platform, we aim to deliver more precise, reliable, and comprehensive search results to our users. This partnership represents a significant step forward in our goal to provide a search engine that users can trust to find the dependable information they need quickly and easily.
In addition, we are very pleased to welcome Stephen Wolfram to Kagi’s board of advisors. Stephen brings years of experience (Wolfram Research was founded in 1987!) running a largely bootstrapped business and growing it to 1,000 employees, which resonates strongly with us. With his extensive experience in catering to the needs of educational institutions worldwide, Stephen brings a wealth of knowledge that we believe will be instrumental in guiding Kagi’s next significant step forward.
Wolfram|Alpha integration in Kagi
We launched our first integrations with Wolfram|Alpha two weeks ago and you have been seeing them for many computational queries already. Today we are taking this further.
Wolfram|Alpha now powers quick access to math, time, unit conversion and factual information in Kagi.
Kagi is now able to immediately answer more complex computational queries.
And for diehard fans of Wolfram language, we even support direct evaluation of commands.
In addition, today we are launching rich knowledge graph widgets powered by Wolfram|Alpha.
And last but not least, we are launching instant summary boxes that show information as you type, saving you an entire search!
It is a very powerful feature that makes sense to be implemented directly in the browser. We will be bringing this into Orion browser and it will be open for any other browser to implement as well.
What’s next
We hope you try and like the Wolfram|Alpha integration in Kagi. Please let us know what you think via kagifeedback.org.
We will be enabling our Assistant to use Wolfram|Alpha information as a powerful source of truth for those situations where you want to interact with an LLM to get answers. And all this will come at no additional cost for our users.
Looking forward, we acknowledge the importance of providing structured, accurate, and swift informational widgets, enabling users to quickly access the information they need and spend least amount possible in the search engine. We already have a number of them like the weather, time, calculator, internet speed test, translation and color widgets - just to name a few.
We will continue adding them, including a more robust calculator widget, sport scores and stock price charts, and we are even thinking of providing a consumeable API for users to add their own widgets to Kagi search results triggered on demand (and shareable with others via an open-source repository). Stay tuned!
–
Discuss on Hacker News