Gemini Notebook
Google's source-grounded research tool, now with code
- Overview
- Formerly NotebookLM, Gemini Notebook was renamed by Google on July 16, 2026, and remains a standalone research tool at notebook.google.com. You upload documents, PDFs, URLs, and notes; the AI answers questions, builds multi-source syntheses, and generates Audio and Video Overviews grounded exclusively in your sources. The June 2026 update added agentic research skills and native code execution inside notebooks, powered by Gemini 3.5.
- Why it matters
- Gemini Notebook is one of the few AI research tools where the free tier is genuinely useful at scale, which drives rapid adoption in enterprises that already run Google Workspace — the marginal per-seat cost is zero on qualifying plans. The July 2026 rename signals Google's intent to embed this tool across Search, the Gemini app, and Classroom, raising realistic lock-in questions for teams that build workflows around notebooks. The addition of code execution moves it from a Q&A layer into light-weight data analysis territory, putting it in closer competition with tools like ChatGPT's data analysis mode. Watch for pricing pressure as Google tightens free-tier limits to push users toward paid Google AI plans.
- In practice
- Consulting and strategy teams typically create one notebook per engagement, loading contracts, reports, and competitor filings, then using the chat to draft summaries and briefing documents with citations traceable back to the source. The agentic research mode (added June 2026) lets the tool suggest and ingest additional sources mid-session, cutting research setup time. The primary honest limitation is that the tool is only as good as what you upload — it does not browse the web in real time by default, so fast-moving topics require users to manually refresh sources.
- Best for
- Researchers, consultants, and knowledge workers who need to interrogate large document collections and produce structured outputs without leaving their source material
- Pricing
- Free tier: 100 notebooks, 50 sources per notebook, 50 chats/day, 3 Audio Overviews/day — no credit card required. Higher limits bundled with Google AI Plus (~$4.99/mo), Google AI Pro ($19.99/mo), and Google AI Ultra ($99.99–$199.99/mo); no standalone Gemini Notebook subscription exists. Teams on Google Workspace Business Standard or above get Plus-level access at no extra line item.
Key features
- AI grounded exclusively in your uploaded sources with inline citations
- Audio Overviews and Cinematic Video Overviews for podcast- and film-style content summaries
- Native code execution via a secure cloud computer inside each notebook
- Agentic research mode: suggests and adds sources via Google Search
- Multi-source synthesis across PDFs, Google Docs, URLs, EPUBs, and more
Quick answers
- What is Gemini Notebook?
- Formerly NotebookLM, Gemini Notebook was renamed by Google on July 16, 2026, and remains a standalone research tool at notebook.google.com. You upload documents, PDFs, URLs, and notes; the AI answers questions, builds multi-source syntheses, and generates Audio and Video Overviews grounded exclusively in your sources. The June 2026 update added agentic research skills and native code execution inside notebooks, powered by Gemini 3.5.
- Why does Gemini Notebook matter?
- Gemini Notebook is one of the few AI research tools where the free tier is genuinely useful at scale, which drives rapid adoption in enterprises that already run Google Workspace — the marginal per-seat cost is zero on qualifying plans. The July 2026 rename signals Google's intent to embed this tool across Search, the Gemini app, and Classroom, raising realistic lock-in questions for teams that build workflows around notebooks. The addition of code execution moves it from a Q&A layer into light-weight data analysis territory, putting it in closer competition with tools like ChatGPT's data analysis mode. Watch for pricing pressure as Google tightens free-tier limits to push users toward paid Google AI plans.
- What is Gemini Notebook best for?
- Researchers, consultants, and knowledge workers who need to interrogate large document collections and produce structured outputs without leaving their source material
- How much does Gemini Notebook cost?
- Free tier: 100 notebooks, 50 sources per notebook, 50 chats/day, 3 Audio Overviews/day — no credit card required. Higher limits bundled with Google AI Plus (~$4.99/mo), Google AI Pro ($19.99/mo), and Google AI Ultra ($99.99–$199.99/mo); no standalone Gemini Notebook subscription exists. Teams on Google Workspace Business Standard or above get Plus-level access at no extra line item.
Seen in recent stories
Where Gemini Notebook showed up in the last 90 days of KeyNews editions.
Know the terms
Glossary entries that explain what Gemini Notebook is built on.
RAG (Retrieval-Augmented Generation)
A technique that retrieves relevant documents from an external knowledge base and feeds them to a model alongside the user's query. RAG reduces hallucination and keeps responses grounded in current, factual data.
Grounding
Techniques that anchor AI outputs in verifiable facts by connecting models to external knowledge sources. Grounding reduces hallucination and is essential for enterprise use cases where accuracy is non-negotiable.
Hallucination
When an AI model generates confident-sounding but factually incorrect or fabricated information. Hallucination is the number-one barrier to enterprise AI adoption and a major focus of current research.
Context window
The maximum number of tokens a model can process in a single request, including both the prompt and the response. Larger context windows (100K-2M tokens) let models ingest entire codebases or documents at once.
Models behind it
The models Gemini Notebook runs on, offers, or competes with.
More research & analysis tools
New tools drop every week.
ONE BRIEFING · EVERY FRIDAY · FREE
Free. Unsubscribe anytime.