Google has updated its Deep Research agent in the Gemini API and introduced a "Max" tier built on Gemini 3.1 Pro. The upgrade turns the tool into a fully autonomous research agent: you give it a topic, it searches the web on its own, reasons across sources, and delivers a complete report - including charts and infographics - with citations throughout.
The Max tier handles both public web searches and your private data. It connects to internal sources through MCP (a protocol that lets AI tools pull from outside data sources, like your company's internal documents or databases alongside live web results). The standard Deep Research tier remains available for lighter workloads.
What It Actually Produces
The output isn't a bullet-point summary - it's a structured, professional-grade report. The agent pulls from multiple sources, cross-checks them, and generates visual elements like charts natively rather than dumping raw data into paragraphs.
For research-heavy work - market analysis, competitor breakdowns, technical documentation - this is a different category from asking ChatGPT to research a topic. Standard chatbot research returns a few paragraphs with a handful of sources. Deep Research Max runs an extended autonomous search and consolidates findings into something structured enough to hand directly to a client or drop into a presentation.
The MCP integration is the detail that separates this from competing research tools. Most AI research agents are limited to public web results. Searching private data alongside web results - in the same workflow, with the same agent - is useful for business contexts where internal documents need to factor into external analysis.
Access and Availability
Deep Research Max is currently available through the Gemini API, which means it's aimed primarily at developers and businesses building applications, not casual users opening a browser tab. Whether Google will surface the Max tier in its consumer Gemini interface hasn't been announced.
The competitive context is clear: OpenAI has its own Deep Research feature in ChatGPT, and Perplexity built their entire product around autonomous web research. Google is differentiating on report quality and private-data integration - capabilities that competitors haven't matched at the API level yet.