The AI CAD agent is vision-capable: drop in a hand sketch, a photo of an existing part, or a screenshot, and it will read it, ask clarifying questions, and write parametric OpenSCAD that matches. After every generation it sends a 4-view technical sheet of its render back to itself for a self-critique pass — so revisions converge against your reference without you having to compare side-by-side.
After the first render, the agent's render engine produces a single image composed of four orthographic views (front, side, top, isometric). That sheet is appended to the agent's next context, alongside your original reference, with the question "does the render match the reference? If not, what specifically should change?" .
The agent will either:
The loop runs up to twice by default — long enough to converge, short enough not to burn credits.
Sketches are the single highest-ROI input. A few habits make them dramatically more useful:
For mating to standardized hardware, screenshots of the spec sheet (motor bolt circle, PCB outline, extrusion cross-section) work brilliantly. The agent can read the dimension callouts directly and clearance-fit holes without you having to type the numbers.
Example prompt with a NEMA17 spec-sheet screenshot:
The composer accepts mixed input. Common stacks:
The agent can recognise that a hole is roughly central, that a chamfer exists, and that there are four mounting holes — but the exact millimetre values are far more reliable when you put them in the prompt (or write them on the sketch). Treat the image as the shape, your text as the specification.
For pure mesh-style image-to-3D (figurines, props, characters), use one of our purpose-built generators instead — they output STL meshes, not parametric code:
Mesh-style AI for figurines, props, art, and decor. Outputs STL.
Photo of a face → printable 3D bust.
Pet photo → printable 3D figurine.
Open the modeler, drag any image into the composer, and add a one-line prompt. Auto-iterate handles the convergence.