The DropJune 10, 2026via The Decoder
Google's NotebookLM now runs its own cloud computer with code execution and agent-based research
Why it matters
Google is shipping agentic capabilities into a consumer research tool, moving beyond chat interfaces to autonomous workflows. This signals how quickly AI product teams are moving from copilot → agent architectures in real applications.
Key signals
- NotebookLM upgraded to Gemini 3.5 Flash
- Now includes cloud-based code execution
- Agent-based source discovery via Google Search integration
- Internal A/B testing shows 78.2% win rate vs. previous version
- Agentic research capabilities (autonomous source finding)
- Published June 10, 2026
The hook
NotebookLM just went autonomous. Code execution, agent-based research, cloud compute—all built in. Internal tests show 78.2% win rate vs. the old version.
Google is giving NotebookLM a major upgrade. The research tool now runs on Gemini 3.5 Flash, has its own cloud computer for code execution, and can find sources on its own via Google Search. In internal tests, the new system beat the previous version up to 78.2 percent of the time.