Image Source: ChatGPT-4o
Web Guide is a new Search Labs experiment that uses Gemini AI to reorganize Google Search results into clusters based on query context.
The tool employs AI-driven query expansion and a fan-out technique to deliver more nuanced results than traditional ranked lists.
Early tests show it’s especially helpful for open-ended or complex queries with multiple components.
Web Guide appears first on the Web tab for opted-in users, with plans to expand it to the broader “All” results view as the experiment evolves.
Users can easily switch back to standard web results at any time.
Web Guide is a new AI-powered interface that Google is offering through Search Labs, its sandbox for testing experimental features. Instead of displaying results as a simple ranked list, Web Guide groups related web links into sections that reflect different facets of a user’s query.
At its core, Web Guide is powered by a customized version of Gemini, Google’s most advanced large language model. The system processes both the search query and web content, allowing it to surface results that might be harder to find using traditional ranking signals.
To do this, Web Guide applies a query fan-out technique—a method that simultaneously runs multiple related searches to cast a wider net for relevant results. These results are then organized by theme or subtopic, providing users with clearer paths through complex information spaces.
Google suggests trying open-ended searches like:
🧳 “how to solo travel in Japan”
Or more multi-sentence, conversational queries such as:
👨👩👧👦 “My family is spread across multiple time zones. What are the best tools for staying connected and maintaining close relationships despite the distance?”
In these cases, Web Guide can surface not only individual results, but contextually grouped pages—for example, travel safety, budgeting tips, and solo itineraries under one query.
At launch, Web Guide appears only in the Web tab for users who have opted into Search Labs. Participants can toggle easily between AI-organized and standard web results.
Over time, Google plans to test wider integration—including in the general "All" results tab—as the company learns more about where the tool delivers the most value.
Q: What is Google Web Guide?
A: Web Guide is an experimental AI-organized search results page that groups links by topic using Google’s Gemini AI.
Q: How does Web Guide work?
A: It uses a query fan-out technique, issuing multiple related searches simultaneously, and clusters results using Gemini’s understanding of the query and web content.
Q: Who can use Web Guide?
A: Opted-in users of Search Labs can access it in the Web tab of Google Search.
Q: Can I switch back to standard results?
A: Yes. Users can toggle between Web Guide and traditional search listings at any time.
Q: Is Web Guide coming to the main results tab?
A: Possibly. Google says it will begin surfacing AI-organized results in the “All” tab if they prove useful during the experiment.
Web Guide marks another major step in Google’s broader effort to infuse generative AI into search—not just through direct answers, but by rethinking how search results are surfaced and structured.
By organizing results into semantically grouped clusters, Web Guide could help users explore unfamiliar topics more efficiently, especially when queries are ambiguous, exploratory, or multi-faceted.
If successful, the feature may shift how people engage with search—not by replacing the web, but by reshaping how it’s presented.
Editor’s Note: This article was created by Alicia Shapiro, CMO of AiNews.com, with writing, image, and idea-generation support from ChatGPT, an AI assistant. However, the final perspective and editorial choices are solely Alicia Shapiro’s. Special thanks to ChatGPT for assistance with research and editorial support in crafting this article.