GenAI PMDeep Research
A research capability embedded into Perplexity Computer as a built-in skill. For PMs, it indicates the packaging of advanced research into agent workflows.
Key Highlights
- Deep Research packages multi-step research into reusable AI workflows rather than standalone prompts.
- Gemini API developments expanded Deep Research with multimodal inputs, collaborative planning, MCP support, and visual output generation.
- Perplexity Computer embedded Deep Research as a built-in skill, showing how research can become native to agent UX.
- For AI PMs, the core opportunity is designing research orchestration, not just adding a chat feature.
Deep Research
Overview
Deep Research is a product and platform concept that packages advanced, multi-step research capabilities into an AI system or agent workflow. In the newsletter context, it appears both as a capability exposed through the Gemini API and as a built-in skill inside Perplexity Computer. Rather than treating research as a one-off prompt, Deep Research represents a structured workflow that can search, ingest multimodal inputs, synthesize sources, and generate richer outputs such as summaries, plans, charts, or infographics.For AI Product Managers, Deep Research matters because it signals a shift from standalone chat interactions to embedded research orchestration. The key product insight is not just better answers, but better packaging: research becomes a reusable system capability that can be invoked inside agents, apps, and user journeys without forcing mode switches. This has implications for UX design, workflow automation, evaluation, source handling, and how teams differentiate AI products in domains where depth, evidence, and context synthesis matter.
Key Developments
- 2026-01-07: Phil Schmid shared that the Gemini Interactions API (beta) supports multimodal inputs for Deep Research, 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 iterative outline creation through a `collaborative_planning` flag.
- 2026-04-30: Philipp Schmid published a getting-started guide for building and running Deep Research workflows with the Gemini API, covering setup, workflow construction, and execution.
- 2026-06-12: Aravind Srinivas announced that Perplexity Computer now embeds Deep Research as a built-in skill in its agent harness, enabling seamless advanced research without switching modes.
Relevance to AI PMs
1. Design research as a workflow, not a feature. PMs can use Deep Research as a model for building agent experiences that combine retrieval, planning, synthesis, and output generation into a single user-facing capability. 2. Prioritize multimodal and structured input support. The mentions of PDFs, CSVs, images, and custom data highlight that real product value often comes from handling messy enterprise inputs, not just web text. 3. Differentiate through orchestration and UX packaging. The Perplexity Computer example shows that embedding research directly into an agent flow can reduce friction and improve adoption more than simply exposing a separate “research mode.”Related
- perplexity-computer: A key example of Deep Research being packaged as a native agent skill rather than a separate mode.
- gemini-api: One of the main platforms where Deep Research capabilities were launched and expanded.
- gemini-interactions-api: Early API surface where Deep Research supported multimodal inputs and custom data.
- phil-schmid / philipp-schmid: Frequently associated with practical Deep Research announcements, guides, and developer enablement.
- sundar-pichai: Announced major Gemini API Deep Research upgrades, signaling executive-level product importance.
- aravind-srinivas: Connected Deep Research to Perplexity Computer’s agent harness, emphasizing workflow integration.
- claude, cgp, genai: Referenced as tools or ecosystems where “deep research mode” reflects a broader market pattern toward advanced research capabilities.
- andrew-ng: Helped popularize deep research usage patterns through AI power-user education.
Newsletter Mentions (5)
“#17 𝕏 Aravind Srinivas announces that Perplexity Computer’s agent harness now natively embeds Deep Research as a built-in skill, giving users seamless access to advanced research capabilities without switching modes.”
#17 𝕏 Aravind Srinivas announces that Perplexity Computer’s agent harness now natively embeds Deep Research as a built-in skill, giving users seamless access to advanced research capabilities without switching modes.
“#10 𝕏 Philipp Schmid published a developer getting-started guide on building and running Deep Research workflows with the Gemini API, covering API setup, workflow construction, and executing deep research queries.”
#10 𝕏 Philipp Schmid published a developer getting-started guide on building and running Deep Research workflows with the Gemini API, covering API setup, workflow construction, and executing deep research queries. #17 ▶️ Become an AI power user 🌟 new course from Andrew Ng Deeplearning.ai Explains how to use the deep research mode in AI tools CGP, Genai, and Claude to run web searches, summarize multiple web pages, ingest diverse documents and images as prompt context, and generate images, simple games, websites, and apps.
“Philipp Schmid launched collaborative planning in the Gemini API’s Deep Research, letting you use a `collaborative_planning` flag to request and iterate on a draft research outline (e.g., “add a section on power efficiency”).”
#6 𝕏 Philipp Schmid launched collaborative planning in the Gemini API’s Deep Research, letting you use a `collaborative_planning` flag to request and iterate on a draft research outline (e.g., “add a section on power efficiency”).
“Sundar Pichai launched two upgrades to Deep Research in the Gemini API—improved quality, MCP support, and native chart/infographic generation.”
#3 𝕏 Sundar Pichai launched two upgrades to Deep Research in the Gemini API—improved quality, MCP support, and native chart/infographic generation. Deep Research now delivers speed and efficiency, while a new Max mode offers top-tier context synthesis, hitting 93.
“Phil Schmid @_philschmid shared that Gemini Interactions API (beta) now supports multimodal inputs like images, PDFs, CSVs, and custom data via Deep Research.”
AI Tools & Applications Deep Research API : Phil Schmid @_philschmid shared that Gemini Interactions API (beta) now supports multimodal inputs like images, PDFs, CSVs, and custom data via Deep Research. v0 Prompt Directory : V0 @v0 highlighted a prompt directory by v0 Ambassador @rajoninternet as a quick start to ship AI apps. LlamaSheets : Llama Index @llama_index launched LlamaSheets to parse complex Excel files into AI-ready data while preserving semantic context and hierarchy.
Related
Anthropic’s assistant and coding tool ecosystem. The newsletter notes a new capability to use a computer in the background for desktop tasks.
An AI developer advocate and educator who frequently shares Gemini and Google AI Studio workflows. In this issue he highlights Managed Agents for trying Gemini 3.8 Flash.
CEO of Perplexity who often comments on product launches and AI systems. Here he announces portable local runtime compatibility for Perplexity Computer.
AI educator and entrepreneur who shared an AI engineering skills map focused on agentic coding. He is widely relevant to AI PMs for engineering and upskilling guidance.
Google’s API for accessing Gemini models. The newsletter says Gemini 3.7 Flash is available in it and being rolled out to paid users.
CEO of Google who announced new Gemini voice capabilities rolling out to Google AI subscribers. His update highlights consumer and productivity integrations for Gemini.
Perplexity's computer-use product or runtime referenced as having a fully local version. It matters for workflows that need local agent execution.
Google’s interactions-oriented API for model and agent workflows. The newsletter notes it reaching GA and being available as an npm skill.
AI product and developer advocate who shares predictions on generative AI trends. Relevant for AI PMs tracking market direction and product strategy.
Stay updated on Deep Research
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free