Gemini Advanced Rolls Out ‘Deep Research’ As First Agentic Feature [U]

Gemini Advanced subscribers are getting access to a new “Deep Research” capability. It is the “first feature in Gemini” to bring Google’s vision of agents that can perform complex actions on your behalf.

Update 12/20: Deep Research is now available for Gemini Advanced users in over 45 languages and more than 150 countries.

Original 12/11: First previewed at the end of Made by Google 2024 in August, you ask Gemini a research question and it will create a multi-step plan. You will be able to revise that plan, like adding more aspects to look into.

Related: Google announces Gemini 2.0 with agentic focus, coming to Gemini app
Google details Gemini 2.0 Project Astra capabilities, ‘Mariner’ browser agent

Once approved and “Start research” is clicked, Gemini will be “searching [the web], finding interesting pieces of information and then starting a new search based on what it’s learned. It repeats this process multiple times.” Throughout the process, Gemini “continuously refines its analysis.”

The end result is a “comprehensive report of the key findings” that’s organized into sections/headings. Gemini will note “Sources and related content,” as well as link to “Researched websites.” You’ll find “helpful, easy-to-read insights” and a conclusion, with the ability to export to Google Docs.

Framed as a “personal research assistant,” Google says Gemini Deep Research takes a “few minutes” instead of several hours.

Deep Research is rolling out today to Gemini Advanced in English on desktop and mobile web. In the top-left model picker, select “Use 1.5 Pro with Deep Research.” This is coming to the mobile in early 2025.