
kagi.com
August 21, 2026
3 min read
71/100
Summary
Kagi updated its Search and Assistant products on August 21, 2026, adding a redesigned Stocks widget, expanded Assistant search tools, and new retention controls for temporary chats. The Stocks widget now supports exchange-traded funds alongside individual stocks, includes price charts, and animates transitions between selected time windows. Kagi says the widget will appear more often in relevant searches. Search users can also enable a setting that automatically removes paywalled links from results. Kagi Assistant now renders links, Markdown, and LaTeX in user messages. Users can search across all conversation threads, sort results by recency or alphabetically, and use “/” to begin filtering by folder. Temporary Assistant threads can be retained for 24 hours, seven days, or 30 days. The update also includes bulk export of Assistant chats, controls for prompt submission behavior, expandable thinking sections, code-fence syntax highlighting, and protections intended to prevent search-engine indexing of shared Assistant threads. Additional fixes cover Search lenses, shortcuts, Quick Answer source handling, URL behavior, mobile navigation, web-search toggle persistence, speech-to-text pauses on Android, iOS login, and Kagi Translate extension and preset issues.
Key Takeaways
What the discussion said
Although the announcement concerns filtering paywalled links, the AI-relevant discussion quickly became a referendum on whether search is being replaced by assistants. Kagi’s assistant drew unusually strong praise because commenters see it as search-grounded rather than a generic chatbot: it looks for sources first, sticks closer to checkable facts, cites credible material, and can surface alternate product names that defeat ordinary keyword search. Several readers now start with it instead of a conventional results page, especially for research or troubleshooting where SEO clutter has made manual search exhausting. The enthusiasm is tempered by a clear diagnosis of why AI search feels necessary. The web has become dense with spam, content farms, ads, and half-answers, so assistants save time by navigating a degraded information ecosystem. But some commenters reject the conclusion that a fluent summary should replace links. They argue that models can omit context, flatten genuine ambiguity, and confidently deliver an answer where the underlying evidence is uncertain. The preferred compromise is an AI tool that remains anchored to retrieval and gives users source-level control. Filtering inaccessible pages can improve a search-assisted workflow for people unlikely to subscribe, but it also risks steering AI-era discovery away from the original reporting that produces reliable facts.
Where opinion split
The sharp split is over whether AI assistants should displace ordinary web search. Supporters say a retrieval-first assistant beats manual searching through SEO debris and finds relevant information that keyword queries miss; skeptics say polished summaries hide uncertainty and should remain secondary to inspectable source links.
Community Sentiment
Positives
Concerns