Google AI Edge Foresight is a new competitor to the AI note-taker Granola and similar tools. The Mac app can work completely offline, utilizing the on-device EmbeddingGemma 2 model with 740 million parameters, to capture meeting notes across apps, including those from in-person meetings.
- How Google AI Edge Foresight Works
- Google’s Strategy Behind the Release
- A Crowded Meeting Note-Taker Market
- Key Features at a Glance
- What This Means for Users
- Why Offline AI Note-Taking Matters
- How It Compares to Cloud-Based Alternatives
- Getting Started with Google AI Edge Foresight
- The Future of Local-First AI Tools
This launch follows Google’s release of an AI-powered dictation tool in April that worked with local models. The same team is behind both projects.
How Google AI Edge Foresight Works
The app shares similarities with the popular AI note-taker Granola. It features a split-screen view with the ability to write shorthand notes on one side and AI-generated notes on the other side.
Like Granola, it also lets you take manual notes while transcribing the meeting. In Google’s app, you can view the transcript of the meeting or chat with the Gemma 4-powered assistant to get answers.
Knowledge Base and Real-Time Answers
Users can upload documents including PDFs, Google Docs, Microsoft Office formats, plain text, Markdown, and web bookmarks to build a knowledge base. Using your meeting notes and documents, the app can answer questions in real time if a point related to data in the knowledge base comes up.
Offline Capabilities
On its FAQ page, the company specified that Google AI Edge Foresight is optimized for Apple Silicon and can completely work offline. This means you can work with your meeting notes when you are traveling or in a place without an internet connection.
Google’s Strategy Behind the Release
While Google’s earlier dictation app was an experimental one that didn’t make it to mainstream usage, its new meeting note-taker could be just to showcase the ability of its Gemma series of offline models.
However, Google could very well release a consumer version of meeting note-taker that works across video calling apps through its Gemini apps while relying on its cloud models.
A Crowded Meeting Note-Taker Market
The meeting note-taker space is competitive and crowded. But that hasn’t stopped companies from creating their own tools. In the last few months, dictation company Wispr and scheduling company Calendly released their own note-takers. Meanwhile, productivity startup Superhuman (formerly Grammarly) acquired YC-backed note-taker Fathom last month.
Key Features at a Glance
| Feature | Details |
|---|---|
| Offline mode | Works completely offline with EmbeddingGemma 2 (740M parameters) |
| Platform | Mac, optimized for Apple Silicon |
| Split-screen | Shorthand notes alongside AI-generated notes |
| Assistant | Gemma 4-powered chat for meeting questions |
| Knowledge base | PDFs, Google Docs, Microsoft Office, plain text, Markdown, web bookmarks |
What This Means for Users
Google AI Edge Foresight represents a notable step in local-first AI tools for meetings. The ability to capture notes across apps, including in-person meetings, without an internet connection sets it apart from cloud-dependent alternatives.
Whether Google releases a broader consumer version through Gemini remains to be seen, but for now, the app serves as a demonstration of what on-device models like Gemma can achieve.
Why Offline AI Note-Taking Matters
Many professionals work in environments where internet access is unreliable or unavailable. Conference rooms with poor Wi-Fi, airplanes, and remote locations all present challenges for cloud-based note-takers. Google AI Edge Foresight addresses these scenarios directly by running entirely on your Mac.
The use of EmbeddingGemma 2 with 740 million parameters means the app can process and understand your meeting content without sending data to external servers. This approach also raises fewer privacy concerns, since your meeting notes and documents never leave your device.
Privacy and Data Control
For teams handling sensitive information, local processing offers a significant advantage. Legal teams, healthcare professionals, and executives discussing confidential matters can use the app without worrying about third-party data access. The knowledge base you build remains stored locally, giving you full control over your information.
How It Compares to Cloud-Based Alternatives
Cloud-based note-takers typically offer broader platform support and tighter integration with video conferencing tools. They can also leverage larger models for more advanced reasoning. Google AI Edge Foresight trades some of that capability for independence and speed.
The trade-off may be worth it for users who prioritize offline access and data privacy. For others, a hybrid approach using both local and cloud tools could work best.
Getting Started with Google AI Edge Foresight
If you have an Apple Silicon Mac, you can download the app and begin using it immediately. The setup requires no account creation or internet connection. You simply start the app, begin a meeting, and let it capture your notes.
Uploading documents to build your knowledge base takes just a few clicks. Supported formats include PDFs, Google Docs, Microsoft Office files, plain text, Markdown, and web bookmarks. Once your knowledge base is populated, the assistant can reference it during meetings to answer questions in real time.
The Future of Local-First AI Tools
Google AI Edge Foresight signals growing interest in local-first AI applications. As on-device models become more capable, we can expect more tools that run entirely on user hardware. This shift could reshape how professionals think about productivity software.
For now, Google AI Edge Foresight stands as a practical example of what is possible when AI runs locally. It captures meetings, transcribes conversations, and answers questions without ever connecting to the cloud.
