Reshef

atoms to weights and everything in between... "building something new"

[York Yang @YorkYang5050]

Hear what we @DynaRobotics learnt from the bitter lesson in the past 10 months in production

[Reshef @Reshef_]

@jimbelosic (and yes, Claude designed these parts)
https://t.co/yiuSGTFZ1i

[Reshef @Reshef_]

Claude can actually do CAD now in @Onshape

Here it worked for an hour and built a 4-part monitor arm, starting only from a sketch and description. The trick was to give it the tools to look at its own work.

Introducing: Jarvis Onshape MCP

[Reshef @Reshef_]

Feature request: It would be trivial to make this popup list the tapping config and give forgetful people like me one last chance to review.
@jimbelosic

[Reshef @Reshef_]

@Onshape https://t.co/Gwv6Thta4U

[Reshef @Reshef_]

Everyone asking about constraints... Yes, it can!

[Reshef @Reshef_]

Claude can actually do CAD now in @Onshape

Here it worked for an hour and built a 4-part monitor arm, starting only from a sketch and description. The trick was to give it the tools to look at its own work.

Introducing: Jarvis Onshape MCP

[Reshef @Reshef_]

@fhitch11 Nice! send over any feedback or PRs

[Reshef @Reshef_]

Everyone asking about constraints... Yes, it can!

[Reshef @Reshef_]

Claude can actually do CAD now in @Onshape

Here it worked for an hour and built a 4-part monitor arm, starting only from a sketch and description. The trick was to give it the tools to look at its own work.

Introducing: Jarvis Onshape MCP

[Reshef @Reshef_]

@wgussml dm'd you!

[Reshef @Reshef_]

@MikushRab Awesome work, the NIST dataset is hard! If you haven't yet, try Model Mania, I found that it's a bit easier for the agent. What kind of info is in the rendered validation?

[Reshef @Reshef_]

@Orwelian84 @Onshape Conversation: 467K, but real usage was 85M Tok. Every turn re-reads the prefix cache, so 331 turns got VERY hungry. Even on Max 20x, it's a lot. Notice the input is only 688 tokens, that's what I actually gave the model, the rest is automatic

[Reshef @Reshef_]

@Principal_Jon @Onshape Yes! Would recommend you try and run this, or something like ADAM CAD (same idea as this project). It makes 3D-print-ready files

[Reshef @Reshef_]

@JGoodwillieV @Onshape Yeah it's pretty token-hungry. Lots of images being used for renders, and the work can take lots of turns which eat up cache context tokens

[Reshef @Reshef_]

@aegrabs fine, here you go
https://t.co/Gwv6Thta4U

[Reshef @Reshef_]

Everyone asking about constraints... Yes, it can!

[Reshef @Reshef_]

@coreyward I'm planning on it! Gemini's tool use is less advanced so trying to combine Claude's tools and Gemini's vision. I use Gemini for all my CAM advice already. More coming soon...

[Reshef @Reshef_]

@rusty_ralston @CRudinschi @Onshape Yep! Fully 3D printable. Metal machining coming soon 👀

[Reshef @Reshef_]

@CRudinschi @Onshape Yesterday we used it to make a two-part camera mount, which it got right in one prompt and we then 3D printed and used.
It's still highly dependent on vision model capability to succeed, but the CAD feature complexity is the "easy" part

[Reshef @Reshef_]

@TRobot42069 @Onshape 🫡

[Reshef @Reshef_]

Full writeup with benchmark data: I tested Claude on a dozen reference parts. The (un)surprising result is that the bottleneck isn't CAD execution, it's image understanding. Once you describe a part cleanly, the model builds it reliably.

https://t.co/Q7GJcjtwS2

[Reshef @Reshef_]

Try it yourself:

/plugin marketplace add ReshefElisha/jarvis-onshape-mcp
/plugin install jarvis-onshape-mcp

Or: https://t.co/qX069dnZmX