Google launches Deep Research and Deep Research Max agents to automate complex research

2026-04-21 · Source: The Decoder · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Data Science & Analytics · Depth: Intermediate, short

Summary

Google has launched two new autonomous research agents, Deep Research and Deep Research Max, both powered by the Gemini 3.1 Pro model and available through the paid Gemini API. Deep Research is optimized for speed and low latency, suitable for real-time interactions, while Deep Research Max prioritizes thoroughness for asynchronous background tasks, leveraging extended compute time. Both agents support the Model Context Protocol (MCP), allowing connection to proprietary data sources, and can generate native charts and infographics. They also feature collaborative planning, multimodal input from various file types, and real-time streaming of intermediate steps. Google's benchmarks indicate Deep Research Max significantly improves retrieval and reasoning over previous versions, though comparisons with OpenAI's GPT-5.4 Pro and Anthropic's Opus 4.6 show discrepancies due to differing testing methodologies.

Key takeaway

For Machine Learning Engineers building automated research solutions, Google's Deep Research and Deep Research Max agents offer distinct performance profiles. You should evaluate Deep Research for latency-sensitive applications and Deep Research Max for comprehensive, asynchronous tasks requiring deep analysis and proprietary data integration via MCP, potentially reducing manual research time significantly.

Key insights

Google's new Deep Research agents automate complex research, integrating web and proprietary data with multimodal input.

Principles

• Optimize agent design for either speed or depth.
• Integrate proprietary data via Model Context Protocol (MCP).

Method

The agents initiate a full research workflow via a single API call, pulling from open web and proprietary data streams, then generating sourced analyses and visual reports.

In practice

• Use Deep Research for real-time chat interfaces.
• Deploy Deep Research Max for overnight due diligence reports.
• Connect agents to internal financial databases.

Topics

• Deep Research Agents
• Gemini 3.1 Pro
• Model Context Protocol
• Gemini API
• Autonomous Research

Best for: Machine Learning Engineer, NLP Engineer, CTO, AI Engineer, AI Scientist, Research Scientist

Related on AIssential

• Google’s new Deep Research and Deep Research Max agents can search the web and your private data — Google's new Deep Research agents fuse web and private data, generating visual reports for enterprise workflows.
• Google Deep Research Max: Build Autonomous AI Research Agents in Minutes — Deep Research Max is an autonomous AI agent for comprehensive, cited research and native data visualization via a single API call.
• Gemini for Science: AI experiments and tools for a new era of discovery — Gemini for Science leverages AI agents to automate complex research tasks, significantly accelerating scientific discovery and exploration.
• How to use Deep Research with the Gemini API — The Gemini Deep Research Agent automates complex research tasks, offering collaborative planning and multimodal input.
• Google I/O showed how the path for AI-driven science is shifting — Google is shifting its AI for science focus from specialized tools to agentic, LLM-based systems for autonomous research.
• Deep Research Max: a step change for autonomous research agents — Google's new Deep Research agents provide autonomous, multimodal research with proprietary data integration and native visualizations.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Decoder.