Deep Research

Overview

Deep Research is a workflow or product mode in AI systems that combines web search, source gathering, multimodal document ingestion, synthesis, and report generation into a single end-to-end research process. Instead of asking a model for a quick answer, users give it a broader research objective, and the system plans an approach, retrieves relevant information from the web and uploaded materials, summarizes findings, and produces a structured output such as a report, outline, chart, or infographic.

For AI Product Managers, Deep Research matters because it turns foundation models into higher-leverage research assistants for market scans, competitor analysis, customer and industry research, technical landscaping, and strategy memos. The newsletter frames it as a practical capability for research-heavy PM work, especially as APIs like Gemini add multimodal inputs, collaborative planning, MCP support, and richer output formats. This makes Deep Research not just a consumer-facing feature, but a product capability PMs can evaluate, prototype, and operationalize in internal tools or customer experiences.

Key Developments

• 2026-01-07: Phil Schmid shared that the Gemini Interactions API (beta) added Deep Research support for multimodal inputs, including images, PDFs, CSVs, and custom data.
• 2026-04-22: Sundar Pichai announced upgrades to Deep Research in the Gemini API, including improved quality, MCP support, and native chart/infographic generation.
• 2026-04-25: Philipp Schmid launched collaborative planning for Gemini API Deep Research, enabling teams to request a draft research outline and iteratively refine it with flags such as `collaborative_planning`.
• 2026-04-30: Philipp Schmid published a developer getting-started guide for building and running Deep Research workflows with the Gemini API, covering setup, workflow construction, and query execution.
• 2026-04-30: Andrew Ng’s new course highlighted practical use of deep research modes across tools including CGP, Genai, and Claude for web search, multi-page summarization, multimodal context ingestion, and generation tasks.

Relevance to AI PMs

• Accelerates core PM research workflows: AI PMs can use Deep Research to quickly assemble competitor briefs, vendor scans, market maps, user-problem research summaries, and technical landscape reports that would otherwise require hours of manual browsing and synthesis.
• Enables better product design for research-heavy use cases: PMs building AI features can treat Deep Research as a reusable capability layer for workflows like due diligence, policy analysis, support escalation analysis, procurement research, or domain-specific copilots.
• Improves human-in-the-loop research quality: Features like collaborative planning let PMs shape the outline before execution, making outputs easier to steer toward the right audience, decision criteria, and level of detail.

Related

• Gemini API: A major implementation surface for Deep Research, with ongoing upgrades around quality, planning, and output generation.
• Gemini Interactions API: Early API surface where Deep Research support for multimodal inputs was highlighted.
• Phil Schmid / Philipp Schmid: Frequently associated with developer education and launch updates for Deep Research workflows in the Gemini ecosystem.
• Sundar Pichai: Announced notable Gemini API Deep Research improvements, signaling strategic importance.
• Claude: Mentioned as one of the AI tools offering a deep research mode for practical knowledge work.
• Andrew Ng: Helped popularize deep research usage patterns through educational content aimed at AI power users.
• CGP and Genai: Referenced as tools where deep research modes are applied in practice.
• MCP: Its support in Deep Research suggests broader integration with external tools, data sources, and workflows.