Google NotebookLM

# Google NotebookLM Browser automation skill for notebooklm.google.com — document analysis and audio overview generation. ## Navigation Navigate to `notebooklm.google.com` to access NotebookLM. ## Core Workflow ### Creating Notebooks 1. Click to create a new notebook 2. Add sources to the notebook 3. Ask questions or generate audio overviews ### Adding Sources NotebookLM accepts multiple source types: - **PDF files** — upload documents - **Websites** — paste URLs - **YouTube videos** — paste video URLs - **Text** — paste raw text ### Chat Interface - Ask questions about your uploaded sources - NotebookLM answers based on the source material - Citations link back to specific parts of your sources ### Audio Overview (Podcast Feature) The standout feature — generates a podcast-style discussion (about 10 minutes): - Two AI hosts discuss your source material - Creates engaging, conversational content - Excellent for research synthesis, blog content, and study material - Click the Audio Overview button to generate - Generation takes a few minutes ## Best Use Cases - Research synthesis — upload papers and get a comprehensive overview - Podcast content — create podcast episodes for agents or blogs from any source material - Document summarization — quickly understand large documents - Study material — convert dense content into digestible audio - Content creation — generate engaging audio from written sources ### Managing Notebooks - Organize notebooks by topic or project - Each notebook maintains its own source collection - Share notebooks with collaborators ## No Project System Warning NotebookLM has NO persistent memory across browser sessions. Agents must include full context in every prompt: - Who the user is and their account details - What they are working on and why - The complete goal and any relevant history - All necessary URLs, credentials references, and prior results Never assume the agent remembers anything from previous interactions. ## Running on Mac Minis These browser automation tasks run on Mac Minis via mac-control on port 8200: - **Vault**: 192.168.86.27:8200 - **Bots**: 192.168.86.50:8200 - **Jarvis**: 192.168.86.51:8200 Use the mac-control API to send browser automation commands. Example: ``` POST http://192.168.86.27:8200/execute ```