OCCT

earendil-works/pi) and a basic UI for 3D model inspection, measurement, view, table, and sheet creation. There are two ways to try it: 1. Bring your own agent. Point Codex or Claude Code at studio.cogram.com/skill.md and ask it to follow instructions there. This starts a one-hour Studio session and opens the modelling environment in your browser, connected to your agent. You need to confirm sign up only if you want to save the session. 2. Use Studio’s built-in agent. Submit a prompt at studio.cogram.com and sign up. You receive 50 free credits. Here are two models created by agents: - A simple bookshelf (https://studio.cogram.com/view/shr_1agb21nd4) with two sheets - The Colosseum (https://studio.cogram.com/view/shr_3tm32c64y) [large, can take minutes to load], with two sheets showing dimensioned and annotated views. For now, Studio works best when you use it iteratively. If you ask an agent for a finished, complex model and “let it rip”, it may produce something that looks convincing but doesn't hold up to scrutiny. Agentic modelling feels roughly like where agentic programming was in 2024: useful for speeding up repetitive or bounded tasks but not yet reliable enough to complete long, complex jobs. Recent models have improved at CAD. We expect progress to accelerate as models become even better at reasoning across the different representations used in architecture and engineering: geometry, drawings, images, materials, physical constraints, specifications, regulations, code, etc. Early users and our own experience suggest that agents are already useful design collaborators. They can help with repetitive CAD work, fabrication options, part sourcing and cost estimates. We expect that as models improve, agents will be able to explore many different designs, run simulations, and check constraints across an entire project. CAD will become a shared workspace for humans and agents. Because design decisions made in CAD shape much of what is eventually built, even modest improvements could have wide effects. We’d love to hear your feedback and ideas if you give Studio a try. We’re also hiring across product, engineering and commercial roles. If you’re interested in working on interesting problems involving AI and the physical world, please take a look at our open positions at https://cogram.com/about#careers.

the same level of inherent complexity. Blender isn't bottlenecked in what it can do like FreeCAD is. [1]: https://en.wikipedia.org/wiki/Geometric_modeling_kernel [2]: https://en.wikipedia.org/wiki/Parasolid [3]: https://en.wikipedia.org/wiki/Open_Cascade_Technology [4]: https://github.com/Open-Cascade-SAS/OCCT/commits/master/

r need complex organic 3D surfaces, FreeCAD can work - or at least the LinkBranch did for me, I'll have to test 1.0. However, my biggest complaint is with the CAD engine FreeCAD uses: OpenCASCADE (OCCT) [1]. As with most CAD engines, this thing is OLD. It does not like to make NURBS surfaces with true tangency to other faces, and it really doesn't like when fillits cross edges into other faces. You will spend hours adjusting cosmetic geometry so that dress up features like fillits and chamfers will apply. Unless some group of PhDs with some hardcore C/C++ experience come along or the company that develops OCCT gets some major funding, I don't think FreeCAD will improve enough for day-to-day design of complex parts for a long time. Nowadays, I use Fusion 360. I prefer SolidWorks but Fusion is all my job offers me currently. For a CAD package, and coming from years of FreeCAD, Fusion 360 just works. I have tools for making arbitrary complex surfaces (could still be better), I can create fillets that cross into other faces (most of the time), and I can go back in history and edit features and my model will rebuild itself (to a limit, but even the FreeCAD LinkBranch had more issues than Fusion even though it was better than vanilla 1.19.1 and 1.20 FreeCAD). Fusion also has a proper assembly system, which is essential! You can cheat and create parts in FreeCAD by linking sketches to geometry in other parts, but it can only get you so far before you need to go back in time and everything breaks upon a rebuild. I hate to say it, but FreeCAD has a lot of work to do other than the UI. I want to use FreeCAD but it wastes too much of my time for professional work. I would still use it for simple hobby projects. I could talk for hours on this stuff. [1] https://github.com/Open-Cascade-SAS/OCCT [2] https://github.com/realthunder/FreeCAD/releases