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…
In plain words
AI CAD Harness is a plugin that integrates with Onshape and Autodesk Fusion to assist mechanical engineers directly within their existing CAD tools. Rather than generating standalone 3D models, it reads parts, understands feature trees, and makes edits while maintaining full visibility and control over the design process. The tool is designed for engineers who need AI assistance without sacrificing transparency or the ability to work within their preferred CAD environment.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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 [6] https://github.com/Adam-CAD/CADAM [7] https://x.com/claudeai/status/2049143440508616863?s=20
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com