NotebookLM Adds Code Execution and Exportable Research Artifacts
Gemini 3.5, a secure cloud computer, more than 100 research skills, and office-file exports turn notebooks into deliverable workflows.
Key takeaways
Google published its NotebookLM research upgrade on June 8, 2026 and updated availability on July 16. The workflow combines Gemini 3.5 with Antigravity, can run code and browse from a secure cloud computer, uses more than one hundred curated research skills, and can produce PDF, DOCX, Markdown, text, PNG, SVG, CSV, JSON, XLSX, and PPTX files. Google lists access for Google AI Ultra and Workspace AI Expanded Access customers. Users still control which sources enter a notebook. Before sharing a deliverable, open every citation, verify dates and context, recalculate important numbers, inspect formulas and charts, check file permissions and sensitive data, and preserve a source snapshot with the final version.
Direct answer
NotebookLM can now turn source-grounded research into spreadsheets, presentations, and documents. It still requires source selection and separate validation of every delivered file.
Fact sources
Google published the update on June 8 and revised availability on July 16, 2026.
Google describes Gemini 3.5, Antigravity, secure cloud code and browsing, and more than 100 skills.
Supported outputs include document, data, image, spreadsheet, and presentation formats for listed premium plans.
Six steps for deliverable research
- Define the question, deadline, audience, and allowed sources.
- Add primary sources and exclude unverifiable or unclear material.
- Request an evidence table before document generation.
- Open every citation and verify date, context, numbers, and conclusion.
- Inspect formulas, cells, charts, permissions, and sensitive data.
- Save the source snapshot and final version for review.
Why it matters
Code execution and file generation reduce format handoffs while increasing the surface for propagated errors. Evidence and file security matter more, not less.
Impact for ordinary AI users
Users can produce a report, workbook, and deck from one source set. Time is saved only when evidence and each artifact are independently checked.
Related tools and tutorials
Start with one reversible task, verify version, permissions, cost, logs, and accepted output, then record the result in a team checklist.
AI software and tools · AI account and cost services · AI skill tutorials · AI frontier news
FAQ
Can every NotebookLM user access it?
Google currently lists AI Ultra and Workspace AI Expanded Access.
Does it automatically choose trustworthy sources?
No. Users still control and must verify the source set.
Can exported files go directly to clients?
Review data, formulas, citations, permissions, and sensitive information first.
Source links
- Google: Better research in NotebookLM (published 2026-06-08; updated 2026-07-16)
- Google: NotebookLM
- Google Workspace: NotebookLM
What this means for everyday users
Record question, source list, access dates, citations, calculations, output formats, formula checks, sensitive data, permissions, reviewer, and final version.
Related reading
GitHub Copilot Metrics Add OpenCode and Other Clients: Requests Are Not Prompts
GitHub added totals_by_client to the Copilot usage metrics API on October 23, 2026. Enterprise and organization reports can now show model traffic from OpenCode, Claude Code, Codex, Zed, Copilot CLI, GitHub apps, cloud agents, code review, VS Code, JetBrains, and other clients. This article helps administrators build reliable one-day and 28-day reports without confusing model calls with user prompts. It explains request, session, token, model, and selection-mode fields; separates client traffic from agent-app jobs; and adds checks for unknown identifiers, empty arrays, permissions, and coverage. The result is a governance trend report, not an exact invoice or individual productivity score.
Bayer Shares Production Lessons From 22 Specialist Agents: HTTP Success Is Not Task Success
AWS published Bayer Crop Science’s Agentic Decision Engine case study on October 23, 2026. The production system runs 22 specialist agents over governed analytics workflows, models, logs, and visualization tools. This article turns the architecture into five reusable acceptance checks for enterprise agent teams: persist the state needed to resume work, define identity and authorization at every boundary, scope each agent’s tool catalog, distinguish transport success from task success, and release to a gated group before broader access. It also explains why Bayer’s adoption and resolution figures are evidence about one implementation, not promises for another organization. The focus is operational proof, least privilege, rollback, and observable outcomes rather than prompt polish.
GitHub Copilot in Teams Turns Notifications Into Pull Requests: What to Check Before Review
GitHub updated its Microsoft Teams app on October 23, 2026, so an issue notification in a channel, group chat, or private chat can become a Copilot task that investigates the problem, proposes a fix, and opens a pull request. This article helps development and product teams adopt the workflow without mistaking an automated pull request for shipped code. It explains the consolidated app, repository connection, the November 16 retirement of the legacy GitHub app, and the review boundary. A practical acceptance checklist asks teams to reproduce the issue, inspect changed files, run targeted tests, verify permissions, and keep merge and deployment as explicit human decisions.
IskayPet Connects SharePoint to a Managed Knowledge Base: Validate Permissions Before Answers
AWS published IskayPet’s corporate knowledge assistant case study on October 22, 2026. The system connects Amazon Bedrock Managed Knowledge Bases to existing SharePoint repositories and answers cited questions across retail operations, veterinary care, onboarding, and procurement in four languages and three countries. This article turns the case into a practical acceptance plan for knowledge owners. It checks source scope, inherited permissions, hybrid retrieval, duplicate and fragment removal, citation quality, feedback, and token cost before expansion. It also separates the customer’s reported production results from what another organization should expect. A managed retrieval stack reduces infrastructure work, but it does not remove content ownership, access reviews, evaluation datasets, or human verification of important answers.
Copilot in Visual Studio Adds PR Exploration, a BYOM Migration, and NuGet Fixes
GitHub summarized three September updates for Copilot in Visual Studio 2026 on October 22, 2026. The Git agent can explore an attached pull request and link back to comments and files. Bring Your Own Model remains in preview but now requires the new Agent experience, and previously configured Ollama models must be added again. NuGet Audit warnings can open Copilot Chat with the NuGet MCP server to propose dependency fixes. This article gives .NET developers a cautious upgrade checklist: preserve current settings, validate each feature independently, review package and lock-file changes, run targeted tests and vulnerability scans, and keep a rollback path. Summaries and suggested fixes remain review inputs, not verified outcomes.
Amazon Polly Upgrades Generative Speech: Validate 14 New Voices Without Breaking Existing Apps
Amazon Polly upgraded its Generative engine on October 22, 2026, adding 14 voices across nine locales and making generative Hindi and Finnish generally available. Existing voice names and API calls remain unchanged, so applications do not need a code migration, but generated audio can still change. This article gives creators, course teams, contact-center operators, and accessibility teams a reversible acceptance test. It uses one multilingual script to compare pronunciation, pauses, latency, loudness, and fallback behavior before increasing traffic. It also separates the larger voice catalog from a key limitation: generative voices still do not provide speech marks, so workflows that synchronize captions, highlighting, or animation must keep a compatible engine or another timing source.
Summary
Use NotebookLM to connect sources to deliverables, but validate evidence, calculations, and final files as separate gates.