How Deep Research Works - Mukund Sridhar & Aarush Selvan, Google DeepMind

You’re doing research all the time, we just don't always call it that. From figuring out the right summer camp options for your kids to running due-diligence on an investment opportunity, there are plenty of tasks that take up hours of your day and dozens of chrome tabs. Gemini Deep Research is our initiative to turbocharge this process. In this talk we’ll discuss how we built it, learnings along the way and our vision for the future of personal research assistants.

Recorded live at the Agent Engineering Session Day from the AI Engineer Summit 2025 in New York. Learn more at https://ai.engineer and purchase tickets to our next event, the AI Engineer World's Fair, in SF June 3 - 5 here: https://ti.to/software-3/ai-engineer-...

About Aarush
Aarush Selvan is a Product Manager at Google working on Gemini App. He leads Gemini Deep Research, which enables Gemini to act as your personal research assistant. Before kicking off Deep Research, he led the Gemini Extensions platform which connects Gemini with apps and services (like GMail, Google Maps, YouTube) to provide more helpful responses.

Prior to this, Aarush has been lucky enough to work on products at every part of the machine learning stack - from next generation ASICS to compilers and frameworks and even Speech and NLP technology for the Google Assistant. He's originally from the UK and lives in New York (though you can often find him in the Bay Area!). He has a BS and MS in Symbolic Systems from Stanford University.

About Mukund
Staff ML SWE / TLM at Google Deepmind