Summary
This note tracks the current official product signals around deep research as a category, not just as a single case study. It is meant to help contributors extend the lab’s deep-research coverage with current product positioning from OpenAI and Google.Why It Matters
Deep research is turning into a recognizable agent shape: long-running, source-aware, analyst-style work that gathers evidence, synthesizes it into a report, and increasingly connects to trusted or private systems. That makes it useful across case studies, platform comparisons, and future starter projects.Scope Notes
Included:- OpenAI’s current deep research positioning in ChatGPT
- Google’s developer API framing for Gemini Deep Research
- Google’s June 2026 Interactions API general-availability shift
- current Google ADK and A2A bridge signals for Interactions-based agents
- implementation walkthroughs for one specific UI
- benchmark deep dives beyond what the official product pages mention
- broader research-assistant tooling that is not framed as deep research
Source Map
- Introducing deep research: OpenAI describes deep research as a multi-step internet research agent and notes the February 10, 2026 update that added MCP and app connections, trusted-site search controls, and improved progress tracking.
- Build with Gemini Deep Research: Google exposes Gemini Deep Research through the Interactions API and frames it as an embeddable agent for long-running context gathering and synthesis.
- Interactions API: our primary interface for Gemini models and agents: Google says the Interactions API reached general availability on June 22, 2026 and now serves as the primary interface for Gemini models and agents.
- Gemini API docs and Interactions overview: the current docs recommend the Interactions API for new projects and frame server-side state, background execution, and resumable interaction flows as the default developer surface.
- Building agents with the ADK and the new Interactions API plus the Gemini Enterprise Agent Platform ADK guide: Google now connects the Interactions API to ADK-managed tools, A2A bridges, and enterprise deployment paths instead of treating deep research as an isolated product leaf.
Synthesis
Four stable signals stand out across these sources:- Deep research is being framed as work product, not just chat. OpenAI describes analyst-level reports built from many sources, while Google frames Deep Research as a long-running synthesis agent.
- The product boundary is moving beyond public web search. OpenAI added MCP and app connections plus trusted-site restrictions in the February 10, 2026 update. Google keeps pushing the same direction through connected data, managed tools, and long-running interaction state.
- Google is no longer only saying “Gemini Deep Research exists.” The stronger June 2026 signal is that Interactions API is now the primary interface for Gemini models and agents, with Deep Research becoming one concrete surface on top of that wider runtime model.
- Developer-facing agent systems are absorbing more of the product shape. Server-side state, resumable background work, tool execution, and A2A bridges now show up in the same interface family that previously looked like a single research-agent feature.
Contributor Implications
- Extend Deep Research Agents with a short section that distinguishes end-user deep-research products from the developer-facing runtime surfaces that now expose the same agent shape.
- Cross-link future updates with Agent Frameworks, Protocols And Interoperability, and the Deep Research Agent Starter so the note points to durable implementation surfaces instead of remaining a pure market snapshot.
- Route future curation through the Reference Notes hub and the Contributor reading path so product-signal refreshes stay attached to repo-native drafting rules.
Gaps And Follow-up
- Expand Deep Research Agents with a short product-signals section on Gemini Interactions API as a default developer surface for long-running research agents.
- Add a follow-up note focused on evaluation and trust boundaries for long-running research agents that mix built-in agents with framework-owned outer loops.
- Revisit whether a starter project should support trusted-source constraints or server-side interaction state alongside MCP-connected private data in a future iteration.
Update Log
- 2026-06-24: Refreshed the note around Google’s Interactions API general availability and its new role as a primary Gemini agent interface.
- 2026-04-23: Added a contributor-facing product-signals note based on current OpenAI and Google sources.