alt Hacker NewsShow HN: AI CAD Harness
Hi HN, I'm Zach, one of the co-founders of Adam (https://adam.new).
We've been on HN twice before with text-to-CAD/3D experiments [1][2]. The honest takeaway from those threads: prompt-to-3D model web apps are fun, but serious mechanical engineers don't want a black box that spits out an STL. They want help inside the CAD tool they already use, with full visibility and control over the feature tree.
So we built that. Adam is now a harness that integrates directly with your CAD. It reads your parts, understands the existing feature tree, and edits it for you agentically. We are now live in beta on Onshape and Fusion! [3]:
Install link Autodesk Fusion: https://fusion.adam.new/install
Install link PTC Onshape: https://cad.onshape.com/appstore/apps/Design%20&%20Documenta...
Things people are using it for today: - "Merge redundant features and clean up my tree" - "Rename every feature so the tree is actually readable" - "Round all internal edges with a 2mm fillet" - “Parametrize my model” - Along with of course, using Adam to generate CAD end-to-end!
A few things we care about that aren't obvious from the listing:
1. From the start we have always believed in CAD as code as the right abstraction. Our harness leverages Onshape's FeatureScript and Python in Fusion heavily.
2. We run an internal CAD benchmark across frontier models. There has been a massive jump in the spatial reasoning capabilities of recent models, particularly GPT 5.5 and Opus 4.7 [4] [5]
3. We open-sourced our earlier text-to-CAD work [6]
A note on the Anthropic Autodesk connector that shipped a couple days ago [7]: We think it's great for the space and validates the direction.
Where Adam is different: - Model-agnostic. We pick whichever frontier model is winning on each task type from our own internal bench, instead of being tied to one lab. - We live natively in your CAD apps and are actively building integrations across all programs
What would you want an in-CAD agent to do that nothing does today?
[1] https://news.ycombinator.com/item?id=44182206
[2] https://news.ycombinator.com/item?id=45140921
[3] https://x.com/adamdotnew/status/2050264512230719980?s=20
[4] https://x.com/adamdotnew/status/2044859329329893376?s=20
[5] https://x.com/adamdotnew/status/2047795078912172122?s=20
Comments
As someone with a background in mechanical engineering, I'd love to be able to automate CAD design as it's quite tedious and only fun like 5% of the time, but I've tried these tools and I really don't think text-to-CAD is the right approach. It usually takes longer for me to come up with an accurate written prompt to fully dimension what I need than to just grab my space mouse and do it.
Been following you guys a while, seems like you've been gaining some traction recently, lets goo and congrats!
I have been working on GrandpaCAD[0] for a while, a very similar product. I thought of you as my biggest competitors but noticed recently you are focusing more and more on professionals while I am focusing on total noobs in modeling who just want to whip out a quick model. So I guess we are not competitors anymore?
My evals[1] show that Opus 4.7 and GPT 5.5 are very comparable in terms of generation quality, but GPT 5.5 is slower and costs sooo much more in my harness. And the original breakthrough model was Gemini 3.1. I'm curious do you have more written about your benchmarks setup?
If you want to chat email is in my profile. Btw, just met "your"(?) neighbour on a plane a couple of days ago. World is small.
[1]: https://grandpacad.com/en/blog/public-benchmarks-misled-me-o...
This looks interesting and promising! But I'm confused about your business model and pricing, which mentions "creative generations"? I'd like to understand it better before investing time into this.
Is the internal data model of fusion structured enough to be understood with a text-based LLM? Or do you need to basically screenshot the render to understand what is happening?
Would a more CAD-as-code based approach to CAD design be more suitable?
Just like, LLMs have an easier time to build a presentation with latex than with powerpoint...
From the OnShape demo videos in the tweets, it looks like sketches are unconstrained. Can this create constraints or other parametric relationships between entities?
And does this use your OnShape API quota? If it's making a new API call for each individual feature, I could see this blowing through the annual quota very quickly. What does this look like in practice?
There are more elegant solutions to this problem. Why are you trying to get an LLM to work with bloated, archaic tools that you have to rent from a feudal lord in the cloud when there are free open-source alternatives like OpenSCAD.
This is just one example of a superior tool that's natively easy for LLMs to interact with, because the source files are just composable scripts containing lists of shapes and then lists of tools and parameters to apply to the shapes.
I wrote a simple set of system prompts you can use in any repo to show any LLM how to make SCAD files with a whole bunch of cool examples. This is just another example where walking away from the bloated, inferior feudal system of SaaS and cloud models leads to simpler processes and outcomes with superior results in less time, for free.
> Adam is now a harness that integrates directly with your CAD
It does not integrate with "my" CAD, which happens to be none of the two closed-source, closed-ecosystem, commercial products you built your tool for.
[dead]
My friend is an electrical engineer. He designs circuit boards for a living. We were having dinner the other night, and when the topic of AI came up he told me rather confidently that he didn't think AI was coming for his job anytime soon.
I kind of cautiously disagreed. He told me that the applications he used had no tooling for AI.
I basically said "give it six months". I think in my googling now, it's already here.
Mechanical Engineer here, stop using AI to deal with the most enjoyable part of design PLEASE
An automated drafting too where I can describe design intent and requirements would be a million times better, especially if it is CAD context aware.
I would say around 5-20% of mENG is not actually modelling, the endless pursuit of text to cad and other ai works is both not helpful and not enjoyable
(PS: The feature tree renaming does look very useful)