StoryGold provides a foundation model trained on a large parametric CAD dataset that can generate fully editable 3D designs while preserving dimensions, constraints, and feature hierarchies. The model integrates via APIs with standard CAD tools, allowing engineers and developers to query or modify designs through natural language or code and seamlessly feed the output into simulation, analysis, and manufacturing workflows.
Funding
$3.4M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
2OFounders
Product
Problem
Design engineers and developers often rely on generic AI models that cannot preserve the parametric intent of CAD files, such as dimensions, constraints, and feature relationships. This limits the usefulness of AI-generated 3D models for downstream editing, simulation, and manufacturing workflows.
Solution
StoryGold has created a foundation model trained on a massive, purpose-built parametric CAD dataset. The model learns to represent and generate 3D designs while retaining engineering intent, enabling accurate, editable geometry output. By embedding knowledge of dimensions, constraints, and part relationships, the model supports seamless integration with existing CAD, simulation, and manufacturing pipelines. Users can query or modify designs through natural language or code interfaces, receiving outputs that remain fully parametric and ready for downstream processing. The approach offers higher fidelity than general-purpose language models, which lack specialized 3D reasoning capabilities.
Target Audience
Primary customers are mechanical design engineers, CAD software developers, and simulation or manufacturing teams that require AI‑assisted creation of editable, parametric 3D models.
Features
- Large-scale training on terabytes of curated parametric CAD data to capture engineering intent
- Generation of fully parametric 3D models that preserve dimensions, constraints, and feature hierarchies
- Compatibility with common CAD software APIs for direct import and editing of AI-generated designs
- Support for downstream workflows such as finite element analysis, motion simulation, and CNC manufacturing
- API endpoints for natural‑language or programmatic queries, enabling rapid design iteration
- Scalable architecture designed for fine‑tuning on domain‑specific CAD libraries