Manufacturing
Every drawing on the floor,
readable by software.
What we are actually solving
Shop-floor knowledge lives in drawings — thousands of DXFs and PDFs that no system can query. OCR turns them into unreliable text. Four Cad turns them into entities, dimensions, and annotations with their coordinates intact.
How teams use it
01
Drawing digitisation
Extract vector entities, dimension values, and annotation text from DXF, PDF, and SVG drawings — no OCR in the path, so a 12.7 stays a 12.7.
task_type: extract
02
Fixture and placement checks
Ask where a part can sit, whether it is stable in that orientation, and what supports it needs.
task_type: placement
03
Quote and BOM support
Feed exact solid volumes and face counts straight into costing and material estimates instead of retyping them.
task_type: understand
What you send us
- DXF
- PDF drawings
- SVG
- STEP
- IGES
Files are parsed into a structured scene and reasoned over. Uploads are processed for the request, not retained as a library — persist the outputs on your side. Data retention
What we do not claim
Extraction reads what the file encodes. Scanned raster drawings with no vector layer are out of scope — there is no OCR fallback by design.
Try it on one of your own files.
The quickstart is a single curl call. If you would rather see it before you build against it, upload a part in the workbench.
Other industries