Enterprise Knowledge Search
Mentra needed a backend that would let a small team iterate rapidly on AI-native smart glasses while storing fast-changing app data, multimodal notes, and retrieval-ready embeddings for user context.
Reported impact
Mentra can ship new smart-glasses experiences quickly, support accessible captioning and note retrieval, and give third-party developers a backend that extends the platform beyond a single device app.
Mentra built its AI-native smart-glasses platform on MongoDB Atlas from day one so the team could move from prototype changes to production features without fighting database migrations. Atlas stores user settings, operating-system state, and backend data for built-in and third-party apps, while BSON keeps the persistence model close to the way data is handled at runtime in the application. The Mentra Notes app ingests what the wearer sees and hears, stores that multimodal history in MongoDB, and creates vector embeddings for each conversation. Using MongoDB Voyage AI, Mentra can retrieve relevant conversations later from a natural-language query and return summaries or context to the wearer. Atlas profiling and management tooling also helps engineers debug slow queries quickly, which matters for a startup building open-source hardware and software that must scale into manufacturing, accessibility, and always-on contextual AI use cases.
Audio, visual, and settings data from Mentra's smart glasses apps is stored in MongoDB Atlas; Mentra Notes creates embeddings for conversations and MongoDB Voyage AI retrieves matching context later so users can search, summarize, and revisit what they saw or heard.
The number one way is the MongoDB Atlas platform. It is a huge time saver.
We have vector embeddings for every single conversation, and we use the MongoDB Voyage AI tool to recall those conversations based on the user's query.
We store all user settings and OS data in MongoDB.
We've been using MongoDB since day one.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The embedded Organization data lists streetAddress "Charlotte, North Carolina, United States" and addressCountry "US".
The policy lists the address as "Mentra, Inc., 9805 Statesville Road, Suite 6169, Charlotte, NC 28269," in the United States.
Related
MongoDB Sample Sep 9, 2026 Squary AI Squary AI needed to eliminate slow, outage-prone legal search infrastructure that combined MongoDB with OpenSearch and hurt document review speed, cost, and trust. At Quatrini Law Group, Squary AI analyzed more than 460,000 pages and saved over 400 attorney and paralegal hours. Amazon Bedrock · Claude · MongoDB Atlas MongoDB Sample Archived · Aug 29, 2026 Document360 Document360 needed its Eddy AI assistant to answer multi-part documentation questions accurately without breaking access controls or adding a separate vector database to keep in sync. The unified architecture boosted baseline response accuracy to 94%, reduced user dislikes by 30%, and ensured… Atlas Search · MongoDB Atlas · MongoDB Vector Search on Atlas MongoDB Sample Archived · Aug 21, 2026 ElevenLabs Before shifting from AI research to enterprise products, ElevenLabs’ legacy database lacked native free-text search, draining engineering time. MongoDB Atlas 