Google just dropped a significant Deep Research upgrade: collaborative planning, multi-tool orchestration (MCP servers, Code Execution, File Search), multimodal inputs (audio, video, PDFs, CSVs), web-off mode for private data grounding, and Gemini API access in public preview.

The combination I find most interesting for builders: web-off mode + MCP server integration + API access.

That means you can:

• Build a research workflow grounded exclusively in internal company data

• Connect custom data sources via MCP

• Call it programmatically from your own application

Which opens up a category of use cases that previously required custom LLM orchestration: clinical literature review, competitive intelligence pipelines, legal due diligence tools, internal knowledge synthesis.

Google Deep Research workflow

Curious what use cases people here are thinking about. Are you looking at this as:

• End-user tooling (just using Deep Research directly)

• Developer primitive (building applications on top of the API)

• Enterprise workflow integration

Also: the Code Execution tool being available within a research run is interesting — has anyone tested what that looks like in practice for data-heavy research tasks?