During inspections, handovers, and maintenance of technical installations, loose photos are often taken and later processed by hand into a report. EquipLens brings that entire process together in a single mobile app: from photo to a structured, searchable, and exportable overview of equipment and components.
Photos of equipment mean little on their own: without context (brand, type, serial number, location), a photo archive quickly turns into an unmanageable pile of data. Manually labeling and organizing hundreds of photos per project is time-consuming, error-prone, and doesn't produce a consistent, shareable end result. The challenge was to speed up this process without sacrificing accuracy, and without burdening the technician on-site with cumbersome input screens.
We built a native mobile app with .NET MAUI that combines the camera, a local SQLite database, and multiple AI providers (including Gemini, OpenAI, Claude) into a single workflow where photographing, recognition, and reporting flow seamlessly into one another. By designing AI analysis as a swappable provider, the app stays independent of any single vendor and easy to extend.
A working cross-platform app that lets a technician photograph equipment on-site, have it automatically recognized and tagged by AI, and generate a complete, structured PDF or Excel report within minutes — without manual retyping or hours of paperwork afterward.