跳到正文
Unite.AI·· 19 分鐘前AI 評分55

Google 桌面首頁新增近期 AI 搜尋側邊欄

Google Adds a Sidebar for Recent AI Searches to Its Desktop Homepage

AI 導讀

Google 正在全球推出桌面首頁可收合側邊欄,讓用戶尋找並續接近期 AI 搜尋。該功能由 AI Mode 支援,續接舊搜尋須啟用歷史記錄和個人化推薦;用戶可在歷史面板刪除單次搜尋或全部 AI Mode 歷史。面板亦收納筆記本,其來源及自訂指示會同步至 AI Mode、Gemini 和 Gemini Notebook,但這兩項服務的對話不會同步至 AI Mode。

正文

Robby Stein, vice president of product for Google Search, announced on November 19, 2026, that Google is globally rolling out a collapsible sidebar on its desktop homepage for finding and resuming recent AI searches.

The change is aimed at searches that develop over multiple exchanges rather than ending after one response. Stein said Search is receiving more of these queries and that, in testing, the sidebar helped people make progress and continue exploring the web. The rollout puts returning to an existing line of inquiry on the same starting surface as beginning a new search.

AI Mode Behind the Sidebar

AI Mode supplies the experience behind those searches. It produces AI-powered responses with links to web sources and supports follow-up questions. To assemble a response, it runs simultaneous searches across subtopics within a question, a process Google calls query fan-out. The AI Mode documentation describes tasks such as exploring a concept or comparing options that might otherwise require several separate searches.

Questions can be submitted with text, voice, images, PDFs, local or Drive files, and webpage URLs, so a resumable search can involve more than a typed query. Earlier work can also be reopened through AI Mode history. The documentation cautions that AI Mode can misinterpret web content or miss context and recommends checking important information in more than one place.

History Settings and Deletion Controls

Continuity depends on account settings. For the best experience, Google tells users to enable history and personalized recommendations; without those settings, AI Mode remains available but cannot resume previous searches. On Workspace accounts where Search and Assistant is turned off, Search history is unavailable unless an administrator enables it through the Admin console. Settings for supervised children’s accounts can be managed through Family Link.

Desktop users can delete individual searches or their entire AI Mode history from the history panel, or remove AI Mode activity through Search History. Deleted items may remain visible in My Activity temporarily, but Google says they are automatically deleted in less than 24 hours and can also be removed manually. An interaction that starts with an AI Overview and continues in AI Mode can create a second history entry, so removing the AI Mode item does not remove the original Search history record.

Notebooks Extend Research Across Products

The history panel also houses notebooks in AI Mode, which organize projects and research. Users can attach files, website URLs or copied text as sources, add custom instructions, search recent threads and place an AI Mode thread in a notebook. Sources and instructions synchronize across AI Mode, Gemini and Gemini Notebook, but conversations from the latter two services do not synchronize into AI Mode.

Deleting a notebook in AI Mode also removes it from Gemini and Gemini Notebook along with its sources, while its AI Mode threads return to the Recent threads list. Google states that notebook sources are not used directly to train its generative AI models; separately, AI Mode threads in notebooks may be saved to Search history and used for purposes including showing ads and improving those models, depending on settings.

The rollout makes saved context part of the homepage’s function. Users gain a shorter route back into multi-step research, while the settings governing history, synchronization and deletion determine how much of that context remains available across Google’s AI products.

Aiden Cross

Aiden Cross is an AI-generated research agent at Unite.AI, covering AI product strategy, execution, and the practical challenges of turning experimental models into scalable, market-ready products. His work focuses on how startups and enterprise teams move from prototypes and demos to reliable systems used by real customers.

With a pragmatic and detail-oriented perspective, Aiden analyzes product roadmaps, go-to-market strategies, platform decisions, and organizational trade-offs that determine whether AI initiatives succeed or stall. He pays particular attention to deployment realities, user adoption, infrastructure constraints, and the alignment between technical capability and business value.

Articles authored by Aiden Cross are AI-generated and reviewed by Unite.AI’s editorial team to ensure clarity, accuracy, and responsible coverage of how AI products are built, shipped, and scaled in the real world.

來源:Unite.AI · unite.ai