Google’s Gemini Deep Research Gains Access to Gmail, Drive, and Chat Data

TL;DR: Google’s Gemini Deep Research tool can now access Gmail, Drive (Docs, Slides, Sheets, PDFs), and Chat with user permission for research context. Human reviewers may examine data collected. Google confirms connected app information not used to improve generative AI, but warns against using Deep Research for medical, legal, or financial advice.

Google’s Gemini Deep Research tool can now reach into Gmail, Drive, and Chat to obtain data that might prove useful for answering research questions. The tool deputises Gemini 2.5 Pro as an agent, embarking on multistep processes to respond to directives rather than providing immediate responses.

How Deep Research Works

“After you enter your question, it creates a multi-step research plan for you to either revise or approve,” explained Dave Citron, senior director of product management for Google’s Gemini service, in a blog post last year. “Once you approve, it begins deeply analysing relevant information from across the web on your behalf.”

Now Gemini Deep Research can, if allowed, access data in Gmail, Drive (including Docs, Slides, Sheets, and PDFs), and Google Chat for added context. If data stored in Google Workspace might be relevant to research questions, granting Gemini access to that data may lead to better results.

Privacy Considerations and Limitations

There is precedent for this data access among other AI vendors, as providing AI models with access to personal files tends to make them more useful at the expense of privacy and security. Anthropic’s Claude has web-based connectors for accessing Google Drive and Slack, whilst its iOS incarnation can access certain apps like Maps and iMessage.

Google confirmed that information available to Gemini via connected apps such as Gmail and Drive is not used to improve the company’s generative AI. However, the Gemini Deep Research privacy notice includes a noteworthy passage: “Human reviewers (including trained reviewers from our service providers) review some of the data we collect for these purposes. Please don’t enter confidential information that you wouldn’t want a reviewer to see or Google to use to improve our services, including machine-learning technologies.”

The tool comes with a caution not to use Deep Research for matters of consequence: “Don’t rely on responses from Gemini Apps as medical, legal, financial, or other professional advice.”

Mixed Reception

Reviews of Gemini Deep Research run the gamut, from glowing to cautious approval, meh, mixed, and sceptical, with caveats about source labelling accuracy and lack of access to paywalled research. Earlier this year, education consultant and PhD candidate Leon Furze offered a sobering assessment of deep research models’ utility.

“The only conclusion I could arrive at is that it is an application for businesses and individuals whose job it is to produce lengthy, seemingly accurate reports that no one will actually read,” Furze wrote in February. “It is designed to produce the appearance of research, without any actual research happening along the way.”

Looking Forward

Whilst Google’s expansion of Gemini Deep Research access to personal data may improve contextual research capabilities, the privacy implications and limitations around professional advice suggest cautious adoption. The tool joins similar offerings from OpenAI and Perplexity, alongside various open source implementations, in an increasingly crowded deep research market.

Source Attribution:

Share this article