Source-grounded research

How to use
NotebookLM.

Building a focused knowledge space from PDFs, websites, videos, audio, and workspace files, then asking grounded questions or producing cited study and briefing materials.

Open NotebookLM ↗ Official download ↗
What it issource-grounded research assistant Workflows2 UpdatedJuly 2026

NotebookLM is a source-grounded research assistant. Building a focused knowledge space from PDFs, websites, videos, audio, and workspace files, then asking grounded questions or producing cited study and briefing materials. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

01

Access & setup

Find, install, and sign in to NotebookLM

Get into the official NotebookLM experience with the right account and a setup you understand.

  1. 01

    Start at https://notebooklm.google.com/ and confirm the domain before entering account or payment information.

  2. 02

    Availability: Browser-based on desktop, with NotebookLM mobile apps whose feature set can differ from the web experience.

  3. 03

    You need a supported personal, work, or school Google account. Managed accounts require administrator access, and availability depends on supported countries, age, account type, and plan.

  4. 04

    Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.

  5. 05

    Run one low-risk test task before connecting sensitive files, repositories, or workspace data.

  • Use official download pages.
  • Review permissions during setup.
  • Keep installers and applications updated.
02

First session

Your first useful NotebookLM session

Learn the interaction loop using a small task with a clear outcome.

  1. 01

    Create one notebook for one project or subject; notebooks do not automatically share context with one another.

  2. 02

    Add a small, authoritative source set and label what each source contributes.

  3. 03

    Ask a narrow question and open NotebookLM’s inline citations to inspect the supporting passage.

  4. 04

    Generate a briefing, table, mind map, or overview only after checking that the source set is complete.

  • State the outcome before the background.
  • Provide the real source material.
  • Review the result before expanding the task.
03

Quality control

Check the quality of NotebookLM output

Turn a promising generation into an asset you can legally and safely ship.

  1. 01

    Restate the brief, the deliverable format, and where the asset will appear before judging any output.

  2. 02

    Inspect at full resolution: generated media hides its errors at thumbnail size.

  3. 03

    Check the details these systems reliably get wrong — hands, text, logos, reflections, symmetry, and edge artefacts.

  4. 04

    Confirm the licence and commercial-use terms for your plan, and check the output does not reproduce a recognisable style, mark, or likeness you have no right to use.

  5. 05

    Review for accessibility and delivery: alt text, contrast, colour profile, file size, and the exact export format.

  • Inspect at full resolution before approving anything.
  • Confirm commercial-use rights before an asset reaches a client.
  • Keep the prompt and settings with the asset so it can be reproduced.
04

Privacy & permissions

Use NotebookLM safely

Use the platform without surrendering rights, likenesses, or client material you do not control.

  1. 01

    Confirm you hold the rights to every reference image, voice, or clip before uploading it.

  2. 02

    Check whether your plan trains on submitted content, and opt out before uploading client work.

  3. 03

    Never upload a real person's likeness or voice without their explicit, documented consent.

  4. 04

    Review the output for marks, styles, or likenesses you have no licence to reproduce.

  5. 05

    Label synthetic media where your client, platform, or jurisdiction requires disclosure.

  • NotebookLM is grounded in the sources you provide, but generated interpretation can still be wrong. Imported and shared sources can expose underlying material to collaborators; review rights and sharing permissions carefully.
  • Follow your organisation's approved-use policy.
  • Never treat fluent output as authorization to act.
05

Core workflows

Step-by-step ways to use NotebookLM for the work it does best.

Each workflow is a separate guide with its own steps and review checkpoints.

01 WorkflowBuild a trustworthy source notebook

Choose, organize, and maintain a source set that gives NotebookLM a clear and defensible knowledge boundary.

 02 WorkflowCreate a cited briefing from NotebookLM

Move from grounded questions to a briefing document whose conclusions can be traced to source passages.

06

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.

Explore the Troiana AI Hub →