I'm building ShopSpec (https://shopspec.io/) for this kind of workflow. I'm a woodworker and use it for my own home and shop builds.
It's a woodworking domain engine and parametric furniture builder focused on projects like bookshelves, cabinetry, and shop furniture. It works out the parts, joints, cut list, etc.
There is an MCP component in beta (https://shopspec.io/agents) that allows an agent to explore designs while the engine still does the math. To take a design to CAD, a project can be exported as DXF or as a Ruby script that rebuilds it in SketchUp Pro.
It's narrower than Shapr3D, but it might fit the projects you describe.
Cool idea. You might want to tell your LLM to chill on the all caps small text. It's adding eyebrow text to basically every section. Just say 'no eyebrow text. only use caps lock on small text if you absolutely have a good reason to'.
Lol I played around with it a bit and quite like it, it's similar to a tool I've had kicking around in my mind for a while. Man oh man, the amount of text in e.g. the cut lists is just wild :D. Definitely has been my experience that LLMs like to add way too much text to straightforward applications.
This is cool. I have a friend getting in to furniture making and forwarded this, however: (1) You need a metric default outside of the US. (2) >4 shelves does not work. (3) 'Other' hardwood type not possible. (4) Could not find a way to get chamfer to render on slab top.
Having just gone on a tear about why everyone should make their own shop drawings, I have to say that this is really well done. Nice work on this, and good job on incorporating some really good, practical woodworking knowlege.
I try like hell to stay out of the business of plywood boxes, but they're inevitable sometimes. I'll try this out when I have a project it's a good fit for.
This looks very nice. I can see how opinionated it is in a way that it suits your needs well. Cheers!
As an engineer obsessed with the finer details and getting his fix from weekend woodworking by making things just the way I want for fun, and tinkering with newer ways of doing things, some finer details that probably won't make a lot of rational sense, but I really badly want them because it is cool.. I want a more general purpose workflow where I can make anything I feel like... {}toys for kids, bike stand for the shed, A tool wall, Bed for the kids..}. Your approach to doing what you happened to need - bookshelves, workbench etc in a customisable way is very cool. But, I've already made those over the years and need something else.. :-)
Your work gave me a lot of ideas and levelled up what output I can make once I figure out a more general purpose workflow.
ShopSpec looks interesting. I looked at the shoe bench in the gallery, and I see in the 3D drawing there is a finished top piece that overhangs the bench underneath. That part doesn't seem to be in the cut list.
This is amazing -- I was looking for a tool exactly like this to DIY a bookshelf. That said - I noticed none of the patterns had curved edges (or curved sides e.g. for a corner bookshelf. Is that technically possible or out of scope for now?
I’ve started doing some furniture design in CAD and I’ve been wondering how people model plywood. Do you make 3/4” plywood 0.75” thick, or do you use the actual sheet thickness (often, but not always, 23/32)?
Am a furniture maker, professionally. Do mostly hand work or at least more traditional tools, but use CNC with some regularity for jigs, templates, and the like.
If you're CNC cutting parts that need to fit together, you need to measure both your plywood and your cutting tool with digital calipers to the thou. Freud's 1/4" upcut spirals (available at Home Depot) are pretty commonly .245" rather than .250". That's enough that things don't fit.
Yes, I've been burned by this.
Also, if you're just making through cuts on your CNC, reference the bed for the Z-axis rather than the material surface, and a few thou either way doesn't matter.
I'm not even thinking about that kind of precision work.
For a basic bookshelf, the space might be constrained. Say I need the outside dimension to be 24.5" wide. If I'm using 3/4" plywood, do I model it so I have 23" wide shelves or 23-1/16" wide shelves?
Or is it irrelevant? Do you build the box first, then measure and cut the shelves to fit?
The more I think about it, the more I'm concluding that you use 23/32" and then do a lot of measuring and adjusting as you build. Taking a cut list and cutting everything ahead of time is probably a bad idea unless you know your plywood is exactly the right thickness.
In most applications, it doesn't matter if the piece ends up 1/16" (1.5mm for the rest of the world[0]) undersized and I wouldn't worry about it. If for some reason the finished piece had to be 24.5" wide, I'd account for the off-nominal thickness of the plywood and charge more for the hassle of it :-)
Generally though, if you're putting something into an alcove and want a fitted look, you'd build the box undersized by some amount (1/4" to 1/2" depending on how square and plumb the walls of the alcove are), set the box in place, and then scribe a face frame to the walls.
Drawer boxes tend to be where you have to work to the tightest tolances. Side mount drawer slides don't have a lot of allowance for the drawer to be undersized and basically none for it to be oversized. Under mount slides are a little more forgiving, but I definitely still account for my actual material thickness on them. In either case, you're definitely building the drawer boxes to the as-built size of the opening they're going into and not the platonic ideal opening from the plans/drawings.
[0] Yes, I know. Slightly more than that, but this is woodworking tolerances.
> Side mount drawer slides don't have a lot of allowance for the drawer to be undersized and basically none for it to be oversized. Under mount slides are a little more forgiving, but I definitely still account for my actual material thickness on them. In either case, you're definitely building the drawer boxes to the as-built size of the opening they're going into and not the platonic ideal opening from the plans/drawings.
This doesn't work great for what the previous poster is asking about, where something needs to fit into a specific space (the comment about scribing a face frame is mint though), but what I typically look for when I'm building things, whether wood, metal, 3D printed, etc, is to try to find the critical faces and let everything shake out around that.
For example, in the side-mount-slide drawer box situation, you've nailed it: the spacing between the exterior face of the drawer and the interior face of the carcass is critical. What I personally would do for that situation would be something like:
- cut rear carcass rails and drawer front and backs precisely with exactly the right spacing, and probably a few temporary front carcass rails that won't be part of the finished product but can be clamped in place for lay-up
- the drawer sides and front/back get dowels that are drilled referenced to the outer edge of the drawer front/back and outside face of the drawer sides
- a slightly oversized dado in the drawer front/back/sides so that the bottom doesn't need to be made as precisely. It can still fit snug in the slot, but if it's a little oversized or undersized relative to nominal, it's not the end of the world
I build furniture professionally. I mostly do commission work, and largely for people who are remote to me, which means I exchange drawings with clients digitally, usually in the form of a rough render (no wood grain texture applied or anything like that) out of SketchUp or FreeCAD[0].
When I actually go to build anything, I generally do pencil and paper shop drawings, usually 3 views, hidden lines showing joinery, etc. I'll make exceptions for simple projects, but for anything even moderately complicated I do shop drawings. "Moderately complicated" starts at a side table with a drawer, and that's something I've put together more than a few of.
The important output of the drawing process isn't a picture of the finished piece. It's knowing, deeply, how all of the pieces are going to fit together and how they relate to each other in space. It's having an order of operations and assembly in mind. It's knowing where the pain points and hiccups are likely to be. It's a good cut list with notes about e.g. what the shoulder distances are for anything with a tenon on both ends.
I don't doubt that you could accelerate the 3D modeling process with AI or a sufficiently friendly CAD program, just as you could take plans from Fine Woodworking or Popular Woodworking and go directly to the shop and start building. I do doubt that things would go faster or more smoothly in the shop for having done so.
[0] Which depends largely on the complexity of the project. This gossip bench was simple enough to do in SketchUp:
My experience is that if there's a lot of shaping with curves and tangency, FreeCAD is less cumbersome to draw it in and a hell of a lot easier to make changes in.
A little bit unrelated, but I was wondering if you could give any advice on how to better mentally train your mind to understand order of operations and assembly better. Is it just a matter of conscious practice, or is there some technique? I love taking things apart but putting things back together seems to get harder and harder, especially as devices get more complex. I've always wondered how I could do better in this manner, other than taking photos(that end up not being useful), of the disassembly process and hoping I put things back together properly.
Uh, I spent a lot of time playing with Legos as a kid, but if you can find a time machine, there are probably a lot of way more profitable ways to put it to use than giving your past self some Lego sets.
If I'm taking apart things on my car, I'll do one side at a time even if it would be more efficient to do both at once so I have an un-monkeyed-with side for reference if I get confused putting it back together.
I tend to stay away from taking apart and reassembling electronics; I can't fix anything inside anyway unless there's an iFixit guide that I'm blindly following.
Most furniture projects break down into at most three (or thereabouts?) hierarchical steps for any single assembly. Which is to say, my spatial/assembly skills probably aren't actually that developed via building furniture.
Which is to say, great news if you want to build some furniture! Pick a simple project and wade in!
Thanks! The three-way joint where the stretchers come together is wild too. It's a three-way finger joint (for structure) with a three-way miter on top (to get the profiles to come together nicely). Drawing it is one thing, and cutting it is a whole 'nother thing :-D
The beveled profile on the top was the clients' touch. We went through four or five iterations on it. They have great taste and are a ton of fun to work with.
I'm in the middle of ginning two prototypes of a chair meant to go with it. It's as yet unclear if I've made my life any easier than the table or not.
Is it possible to learn something like this later in life? My granddad was a carpenter and had a shop but by the time I was a kid he took up drinking pretty heavily and I barely saw him working. I suck when it comes to mechanical work or something similar but I think I'd enjoy working with wood.
This was a career change for me; I somewhat infamously no longer build software[0]. I went back to school in my thirties to learn furniture making. I had never picked up a hand plane or chisel prior to taking classes. I started with some evening and weekend classes, followed by a couple of weeklong classes before applying to go to school full time.
As with learning any skill, I'd suggest finding a project to work towards to motivate you.
I was fortunate to have two full-time programs to apply to in the Boston area (now one, sadly). The biggest difficulty for finding training is likely going to be finding a place that offers it.
New England has the North Bennet Street School, the Center for Furniture Craftsmanship, Vermont Woodworking School, and maybe a few others. As I'm currently in Vermont, I know the New England scene the best.
Your gossip bench reminds me of some of Alan Peters' pieces, not surprising given the Arts and Crafts style requested by your client and your obvious attention to detail.
For the long term, I have noted FreeCAD + Blender + $ai_model to be a good general purpose workflow that yields more control, and will probably get me lost into the details.
A friend of mine was borrowing the shop of a very well known luthier to build some furniture. I stopped by to check the whole situation out and I found them both with their brows furrowed trying to work out some tolerances for a joint on a scrap piece of paper. As an architect by training, I quipped "at some point you'll have to start making proper drawings of you projects ahead of time", to which the luthier replied "the plans are always the problem, you're better off letting the wood tell you how it should be put it together." to which I had no reply..
Having recently had my bathroom done, I was surprised to see that none of the trades had any kind of drawing or preparation; everything was eyeballed together. Slightly less surprised when there was a catastrophic measuring error.
I have a lot of respect for the intuitive-improvisational mode, and some people can do it brilliantly while playing the violin, but I'm not sure it always works for making things.
My personal experience is that woodworking at hobby grade is a art+science+engineering in varying proportions depending on the person's interests. I can relate to your friend in that almost always, as I work through a project, it evolves in its details, joinery, design (even size as I make my mistakes) etc. However, it is important to visualise _what_ one wants in mind before beginning to mill wood. I sketch so much in various perspectives to narrow that down and try to visualise how my idea would materialise.
If AI could catalyse that first part and help visualise the idea in many perspectives that are easy to tweak and improve, I think it will be a solid base to work upon and change organically as we build it in the shop.
As an amateur wood worker, the main issue is that I can’t cut things as precise as I want. It’ll be a couple mm off, or slightly crooked, or I’ll have cut too much and need to find something to fill in the blanks.
You may call that the art part, but it’s actually the terrible skills part.
I'm with you brother/sister! I recently acquired a small hobby-grade laser cutter that can do 1/4" plywood happily and 1/2" plywood if you ask it really really nicely.
One of the things I intend on doing with it is cutting router templates for parts that I need to make a bunch of with "identical" dimensions. Get it as close as I can with the table saw and miter saw, stick the template to it, and use a flush-cut bit to clean up my slop.
It's a fun tool in its own right, I really get a kick out of designing and cutting tab-and-slot designs. They just fit together so beautifully right off the laser. I get the joy of designing the project and assembling the project without the swearing/frustration bit in the middle.
The grandfather of one of my son's friends was a locally-noted woodcarver --- when his daughter first brought home her future husband, he handed the prospective son-in-law a piece of wood and a knife and asked, "What do you see in the wood?" When the reply was, "A piece of wood.", he took both back rather disgustedly.
His woodcarvings were _amazing_, in particular for his ability to work with the grain and even to chase a single ring so as to make a perfectly shaped, but seemingly impossibly thin and light wing of a bird.
I have started tje POC 2 years ago without AI. When it reached a shape I like I started using AI. Now all code is AI written but I'm still controlling the overall architecture.
Shameless plug: I’m workin on http://partforge.ai right now it’s mostly aimed at 3d printing but it can create laser cut sheet parts with dxf file exports and will support cnc routed parts with drill holes and socket diagrams built in in the near future. Board cut lists as a export is a little further out, but you can ask it for measurements of anything you build and it would probably be a pretty useful tool.
Just a little feedback: one of my most hated dark patterns in design is when you give the user the impression that they can try out your website but they actually can't. That's the case on your website: there is a text field making it seem like you can give your site a spin, but as soon as you hit the submit button, you get a pop-up telling you that you have to sign up first. And that after I already spend some (admittedly small) effort to craft a sample text.
I personally hate that pattern, and my default reaction is to immediately close the tab.
Perhaps you could change the landing page to avoid that negative first impression?
Claude Code is now WAY better at the freecad python api. My product (related to ceramics) does a whole bunch of custom 3d modeling and the new generation of LLMs can go in and make significant changes and basically get it right. They can also deal with a lot of annoying corner cases when you run into them.
I've also had really good success with FreeCAD, and the FreeCAD MCP server. So far I've had it design and build a custom workbench (woodworking project w/ cut list, assembly and hardware instructions, tool and part check lists) as well as a omni-directional differential style robot wheel module for a 3D printing.
I will say the differential wheel module was on the edge of what it was able to do. I had to bump it up to Fable and if I didn't already have a clear model in my head of what I wanted I don't think it could have pulled it off.
All text, but none of these were a one-shot task. There were a few serious gotchas that you need to pay close attention to. It understands problems VERY well when it actually controls the viewport and takes screenshots of the part, unfortunately it REALLY resists that instead preferring to make up a bunch of equations to justify/validate it but these were almost never correct. It frequently got things like axis backwards so when it would test for a potential collision it would test in the wrong direction. Guidance specifically for the axes might help there, I suspect it's assuming different real-world axis (maybe more aligned with the game industry axis than modeling or CAD axis standards).
When I approached those two projects I took different approaches. The workbench I had clear measured physical requirements and desires but no specific design in mind (such as number or size of drawers). I had a long back and forth working out a purely textual project description via Fable chat, I originally wasn't even going to model it in CAD and just build from the textual description. I had just seen someone else post success with FreeCAD + MCP and there were some measurements that were suspect... So I had it model it. It did pretty good entirely on its own but a wood bench is composed of effectively a bunch of differently sized rectangles oriented and put together correctly so it feels like this was an "easy task" for it to complete.
The other side of the coin was that inverted differential omni-wheel. This one I knew mechanically exactly what needed to happen and I wanted to model to make a parametric, re-usable model that could be dropped in to a bunch of different designs. This one needs some complex gearing built which it actually mostly did pretty well. Where it kept failing here was weirdly in the motor placement (it was a stock placeholder mesh of the motor part), it had a sled mount with screw slots to allow a little adjustment of the meshing of the final gears. Over half of my time working with the model was simply trying to get it to point the motor model in the correct direction, fully seated in the sled, with the screw slots accessible and physically not colliding with anything. The next hardest part was composite/boolean joined parts, specifically a couple of gears that are a combination of crown and pinion gear, it couldn't seem to comprehend that adding the two physical objects together wouldn't remove excess material from around one of the sets of teeth.
Kind of a ramble, but let me know if there are any more specifics I can provide.
In my experience the MCP is not needed, it just runs headless FreeCAD using CLI. The MCP can be useful if you want to run FreeCAD on a VPS, and then use ChatGPT e.g. on your phone (optionally via voice). But for local I'd go with the CLI. But they'll do just fine with the MCP, which probably wraps the Python API anyway (ideally, otherwise it could lack some features).
OpenSCAD as well. I bounce back and forth between the two of them a fair bit depending on what I'm doing and which one's going to be more ergonomic for the problem at hand. The Fusion 360 built-in chat thing... not so good in my very limited experience.
I can imagine. I did a bit of poking with blender and the api use got better there as well. For my use case I needed BREPs so stuck with freecad. I'm tempted one of these days where I have a pile of extra tokens to see about converting it to directly use the Open Cascade library since I just need to model and not the UI.
Second this. Since Opus 4.6 there's been a very noticeable bump in accuracy at just doing FreeCAD+Python or OpenSCAD code, usually one-shots things with basically described geometry.
Recently, Sonnet 5.5 got quite good, too, but not at the level of Opus/Fable for complex geometry
Disclaimer: I use it for very precise 3D printing, not woodwork.
I'm now printing my 3rd or 4th totally Claude-generated 3d printed custom project enclosure. Opus 5.5 is quite good - it's been generating CadQuery scripts and exporting them as STL for me, along with image previews and so on.
We haven't collaborated at all but are working on very similar projects, so probably do think a lot alike. I last checked shopspec out when the creator mentioned it in the thread[0] where I first shared Sawdust. I just took a look and it has definitely grown in a similar direction, but I certainly wouldn't attribute that to anything aside from similar people working on similar projects and communicating with a similar visual language.
That's exactly why I built it, I needed my brain visuals to match reality a bit more when building a shed. Curious to hear how it goes! If you run in to any issues please ask your agent to send in a feature request/bug report, or drop me an email (it's in my profile).
RapidCAM.app (https://rapidcam.app) has excellent support for AI. The file format specs are published and open source so AI can easily write an ".rcam" file.
RapidCAM.app is a parametric 2.5D CAD/CAM for CNC and laser with support for rotary axis. RapidCAM.app runs in the browser or as desktop apps. There is no login required. The app is free to use. Privacy is respected. rcamhub.com is the sharing site for .rcam files.
Within the App, you can define your project and then use the built in prompt generator. This creates a prompt with all the details AI could need. Once the AI replies with the file, you can paste it back into the app which will then verify the file for you.
Desktop versions of the app have MCP server built in so AI can control the app directly if that is a route you prefer.
I started RapidCAM for my own use as I found that the CNC was sitting idle simply because firing up a full CAD/CAM package took too long. The idea with RapidCAM is that you can quickly sketch out your job from as simple as you need to as advanced as you want going from unconstrained to full parametric/constrained as required.
I'd say Claude/Codex plus whatever CAD modeling tool you want to use. But if you want to find some existing AI-assisted CAD design platforms, take a look at https://thecadhub.com/category/ai-assisted-design/
Why ruin the fun of a hands-on project with computers? I'm also a hobbyist woodworker/DIYer and enjoy the drawing aspect, thinking through the space, the dimensions, etc. and drawing that out with pencil and paper. Its relaxing and by nature disconnected. I'm not on the clock and trying to build things for customers so speed isn't necessary. The level of accuracy in software is thrown out the window when you start dealing with actual wood that has grain, knots, different sizes, etc. I find myself making adjustments in the shop as a project progresses where fine measurements on paper are mostly useless.
I would argue if you're building plans to make a lot of repeatable items, then you're beyond hobby level.
I understand the sentiment... As a computer engineer who enjoys woodworking because it is tangible, abstraction-free, and in full control right in front of your eyes, the line I draw is not "I won't allow computers into this Zen wood shop". Instead, I use computers to accelerate the error prone parts of human planning, and also expand my cognition by making things visual beyond simple imagination. If I see that Coffee table proportions I had in mind as a CAD model, I may spot any balance issues, and even validate if that is what I was going for aesthetically. Heck, it might even give me a chance to improvise on the design because I have now visualised it outside my mind.
Once the CAD model validates my idea, and gives me a rough plan, the zen part of working with the wood, adjusting for grain, knots etc can begin. Even while making changes on the fly, a visual model of the original plan comes in handy.
I'm not a zero computers zen wood shop person. Just offering a perspective based on my experience. I've also built from others digital plans and my own and find that for my workflow, the higher fidelity doesn't add much value. Maybe its a personal tendency to try and make it pixel perfect and because of that I sink way more time into it than I should. Pencil and paper help me avoid that rabbit hole for woodworking.
> a personal tendency to try and make it pixel perfect and because of that I sink way more time into it than I should.
Now that resonates too close to home...
May be I will come to the same conclusion as you after spending hours/days/weeks into trying out a bunch of things with CAD. Lets see... this rabbit hole feels worthy of jumping into.... (it will be different this time!)
If you have some physical reference, for example a coffee table, you can create an accurate 3D model of that quickly. The agent creates model that can be converted to STEP format and opened with any CAD software.
This might help you? You get a good model that you can start editing towards your own design.
Basically you take few pictures. Three is usually enough of furnitures. The agent uses the pictures to find the exact camera poses and creates a 3D model that minimizes the difference between the object's silhouette in images and in the 3D-model when projected with the virtual cameras to the 2D planes. The agents create the model with python scripts. First using numpy for faster optimization and finally CadQuery for easy exports to CAD formats.
I learned OpensCAD manually but it was so painful because you needed to take into account the most minimal and ridiculous thing using code, so I used Freecad in the end that is way more intuitive and fast with graphical tools.
With code like OpenScad it was just too exhausting just to have to think rationally every single detail. And you spent hours doing the most minimal project.
Then LLMs appeared...
Now I use OpenSCAD a lot because with LLMs you have the absolute control that code gives you without the pain of using your logical/rational mind all the time and taking 1/20 of the time for that.
I create my own furniture as hobby. Mostly I use standard IKEA metallic pieces, standard metric screws.
I generate paper blueprints automatically of how the wood panels must be cut and they cut it for me. My Blueprints are pdfs that I print very similar to IKEA blueprints so the one that cuts the wood can not make a mistake. I choose and provide the panels myself.
It is ridiculous how easy it is now with LLMs to do all of that. I can do a new design in a couple hours, including the pdfs. Most of the code is already created and I just have to reuse it.
I use Claude Code.
From time to time I voluntarily teach children to do just that. Some of them are really good after a couple hours of instruction and some mentoring.
I've had poor luck with LLMs in OpenSCAD. They seem to struggle same as I do. The relatively long rendering times are also off putting. Unfortunately, in my laziness, I've locked myself into Fusion for now, but I do quite enjoy modeling by hand in it.
My curiosity lead me to down this rabbit hole as well. Freecad with the woodworking workbench helped me create my plans initially. Since, have moved on to claude code and Freecad to create python scripts to create and modify my cad drawings. A few things which have been able to incorporate in my plans is to have a 3D design, cut-list, shop drawing for joinery and assembly.
Am working on a workshop designer module with chat interface and freecad sandboxed mcp with a support of multiple LLMs. The goal is to take a paper drawn design and have the system build the cad drawings, cut-list, shop drawings and maintain multiple versions. The challenge is all wood working projects are unique and need different approaches. Trying to resolve this by creating skills - building cabinets, building drawers, framing, etc.
Loved all cool ideas out here and it is good to know that am not the only crazy one out there. Happy building folks!
I'm a developer and a previous commercial concrete superintendent. I built a 3d model designer similar to Autodesk Revit as well as a pdf editor similar to Bluebeam. You can connect MCP to it to build full buildings based of drawings.
I recently used Opus 5.5 to diagnose and discover a certain (niche) cleartext format CAD file. Also for generating small, new CAD files containing a small model for test purposes. All with satisfaction.
Coincidentally, I also seen a (private) demo using GPT-6 Astra designing wall panel joints based on some pre-determined rules, 2D lines specifying the layout, and later altering the design following a hand sketch (photo of a sketch). That looked promising too. It was claimed that spatial reasoning of Astra is elevated, can work well with 3D models and formats.
None of those are production (something to manufacture) level just yet. But if I had time I'd explore this manipulating CAD files by an agent route, opening those files in the usual tools I have at my disposal.
Talking/chatting about 3D is like dancing about architecture in my view, so I think this LLM use route is not sustainable straight, still, my above casual encounters suggest, for simple things, combined with manual adjustments, it may be alright.
I’ll share a story. I wanted to make dxf files for some decorative metal gussets I needed for a project. I find CAD programs unintuitive and tried to use Claude as a tutor. That was a fail, it seemed to assume I was more knowledgeable than I am. So then I tried to describe what I wanted and have it emit python to draw it. Again a fail, it didn’t interpret my descriptions accurately and lacked aesthetic sense. Then I had Claude implement a simple DSL that captured my sense of the geometry and form I was trying to express. I ended up wth a very bespoke Logo like language that did exactly what I wanted. I believe there’s a larger lesson there in AI interaction.
Be aware that AI is really bad at certain kinds of geometry. This can either go very well or very poorly. I'm not aware of many happy cases in the middle.
A simple test is that if the object you are modeling could be described by a brief python program (automating blender/CAD APIs), then the LLM will probably one shot it perfectly. If what you are modeling is a human face or bird, then the LLM is at best a clumsy apprentice. High Kolmogorov complexity is the common thread behind all things that LLMs will struggle with.
It can sometimes be easier to lean on a diffusion model and then trace over the results the old fashioned way. Diffusion completely sidesteps the geometry which helps with design speed.
For realizing designs in physical space, I create a Python library with a DSL that allows us to express all of the components and how they relate with each other. The most important thing this provides is a deterministic way to test the assembly. Then, you take the parameterized relationships between the components and export them into things like three-dimensional views or cut lists, rather than trying to manipulate three-dimensional software as your source of truth. (Although Claude is pretty effective at driving Blender via Python, too.)
I’m doing exactly this (in TypeScript) for buildings / construction. It can’t really do woodworking (not designed for that) but I can confirm that it’s an effective strategy for spatial assemblies.
Stealth-ish startup right now (https://bear.build) but we’re working with some large contractors to develop the product. Assemblies are nested and go from a corner detail through walls or MEP systems to levels to the full building being the ultimate assembly.
For 3D printing, I just ask Claude Code to use text based 3D modeling software, and to
build a directory tree per project (with make to convert to something the slicer can use). I’ve printed non-trivial projects this way (60 parts) without trouble. Be sure to ask it to parameterize the models and put the parameters at the top.
I imagine this would work just as well for CNC wood carving/routing projects, and maybe even for complex assemblies.
Onshape, like Shapr3D, is based on Parasolid and works on desktop and mobile. They added MCP support a few months ago and there’s a lot of people who use it professionally for cabinetry etc. Even before they added MCP support, the way everything can be customized through the FeatureScript language has led to libraries of custom features for woodworking. If everything you’re working on is for fun (non-commercial), your Onshape license is free.
There are some active HN folks who participate in both communities. (Check out Oscar Gallegos, who uses AI to generate depth maps, and carves those into wood using CNC router)
Might be worth a look at https://openscad.org/ which is a free tool which designs in 3d based on a programming language that LLMs find easy to use. Then https://cutlistevo.com/ for optimization and nesting of your cut list.
I had been using Gemini to build OpenScad models. The other day Gemini mentioned CadQuery as an option. It's essentially OpenScad for Python. The big plus is b-rep modeler.
crosstrees.1puni.com, mostly built from my phone while hanging out in her saloon!
For you specifically; if all you want to do is manually have a session and describe the thing you want, and see it take form — that's OpenAI's expertise. Pay 20$, get the desktop app, tell it what you want with as much precision as you can. Don't tell it how (don't force CAD if you don't specifically need it). Give it pictures or a photo of a drawing, any data like wood type, maybe even the machines you have at hand... Just dump it all in there. You'll be amazed.
Anyway, I'll plug India, the boat I've reconstructed and had the absolute privilege of helping design the rig for. So that's my weird hobby that AI helps with... rigging Pirates of the Caribbean-style boats.
(Yes, we actually sail them in our community. There was a race a couple of weeks ago. India's yet to be rigged, so she just tagged along as a fender against the cliffs.)
Not yet fully baked, but I am planning to add a woodworking mode to claydash with natural cutting UI - For now I have a couple of wood materials and there is the ability to extrude + cut faces à la sketch up, which should work for simple projects.
I am a woodworker mostly but do it all on pencil and paper. That said I have a 3d printer and cnc and fusion360 with the Claude mcp connector has been pretty amazing in my tests. One more year and it will be a new world.
I have gotten just "ok" at CAD. I'm not as productive as I should be because I avoid it. Really looking forward to this.
Astra in Codex CLI is good with FreeCAD if you let it use the FreeCAD Python runtime in a headless session. It is good at relying purely on natural language to design and revise. To follow specific CAD techniques you need additional prompting. Highly recommend. Uses quite a lot of tokens.
I do home improvement projects (I've in wall built-in storage, benches and nooks) I am on a clock and i have very little room in which to work. The only tool I have relied on https://www.cutlistoptimizer.com/ I have found that the CAD based tools to be pretty much beside the point for _most_ wood working projects for hobbyists, for a few reasons:
1. First several 3-d design iterations are throwaway reworked because I am constantly measuring the design, clearances and studs. And paper works best here instead of working with clankers which takes way longer.
2. Choosing the right kind of materials: thickness and type of plywood, type of hinges, panels, finished or unfinished. Optimize for simplicity of putting components together is most important.
3. Once the design settles the actual joinery needs to be as simple and efficient e.g. butt joints work well most of the time. A good jig for pocket holes is generally the most needed. You will be surprised how well a staple gun works for creating back panels of cupboards.
Its not that they are not useful, shopspec looks great(good job variodot), its just that I can get further and faster without them for most hobbyist pursuits. I invoke YAGNI most of the time because I constantly ask myself one question: "How can I make this be less time consuming?".
Hey! ShopSpec has a standalone optimizer too separate from the parametric design. Check it out and let me know any feedback - https://shopspec.io/cutlist
I’ve been using an llm to generate both renderings of furniture and the gcode for it to be cut using a cnc and assembled ikea style. One off custom furniture at scale.
I use a combination of openscad, blender to render previews of the full thing, and opcut to generate cutlists. I usually ask the models to generate a workshop pdf with the cutlist and the exploded view of the assembly.
Shameless plug since I work for them, but have your tried Vizcom? We're in the ai-assisted prototyping and design space. Our focus is industrial design but I don't see why you couldn't get assistance with woodworking projects. :)
I’m using Plasticity with an MCP and Astra for 3D printing work, haven’t tried it for woodworking projects yet. It’s decent at modeling medium complexity enclosures and structural supports, so might be worth giving it a try.
Also a hobbyist woodworker. I have had both Claude and Gemini generate files I could open in openscad. I mainly use them to generate STL files for 3D printing but I bet it would work for woodworking as well.
I am not a woodworker but wanted to make a simple dehydrator and had good results getting a cut list and build steps with pictures from Claude and the Sketchup integration.
Since relevant community is here - what are some of the good online resources to learn woodwork? What tools/power tools one needs to know specifically?
You really need to build things to learn and progress. Woodworking for Mere Mortals youtube channel is a good place to start. Start with hand tools and build some very basic things, see what you like doing and progress from there. The caution with all online content is the constant promotions, etc. for recommendations of tools or brands. Look for counter opinions. See if you can go use a tool somewhere before buying, maybe at a local store like Rockler or Woodcraft - they may have classes. What you won't see in online content is how long something really takes, they are probably editing 40 hours of video down into 30 minutes.
In my experience, a track saw is immensely more useful than a simple circular saw or miter saw for finer woodworking or cabinet work. The other two are great for rough carpentry but tend to be harder to use for finer tolerances needed for finer woodworking. They are more expensive but because of the track you will get straight cuts with little setup. I've had issues with a contractor sized table saw even with it built into and secured in a DIY cabinet. Lifting and moving large sheets of plywood or assembled boards like a table top can be prone to more errors than setting up and moving a saw along a track. Really expensive table saws are probably better but as a hobbyist I don't have $3000 for a single tool.
> You more than likely will probably never need a table saw, jointer
Very much depends on available material. If you do have decent square boards or plan on mostly using thick plywood, then yes, you can make a lot of practical stuff easily with miter saw and an improvised track saw, or just a real track saw. Otherwise, you'll want to have a jointer.
The necessity of a table saw is a controversial topic, a lot of guides position it as the only saw you'll need, and while technically that may be true, it's way less safe and an overkill for simple projects. Also, expensive in both money and space, since this is a tool you definitely don't want the cheapest and smallest version of. So I agree with you here. If I had the current experience, I'd get a decent track saw instead of the miter saw, more versatile.
I'd prioritize a router table made with a basic wired trim router and a cheap adjustable baseplate, with dust extraction.
I'm building ShopSpec (https://shopspec.io/) for this kind of workflow. I'm a woodworker and use it for my own home and shop builds.
It's a woodworking domain engine and parametric furniture builder focused on projects like bookshelves, cabinetry, and shop furniture. It works out the parts, joints, cut list, etc.
There is an MCP component in beta (https://shopspec.io/agents) that allows an agent to explore designs while the engine still does the math. To take a design to CAD, a project can be exported as DXF or as a Ruby script that rebuilds it in SketchUp Pro.
It's narrower than Shapr3D, but it might fit the projects you describe.
Cool idea. You might want to tell your LLM to chill on the all caps small text. It's adding eyebrow text to basically every section. Just say 'no eyebrow text. only use caps lock on small text if you absolutely have a good reason to'.
Lol I played around with it a bit and quite like it, it's similar to a tool I've had kicking around in my mind for a while. Man oh man, the amount of text in e.g. the cut lists is just wild :D. Definitely has been my experience that LLMs like to add way too much text to straightforward applications.
lol - something so passive aggressive about this comment.
You could just say you don't like the excessive use of caps.
This is cool. I have a friend getting in to furniture making and forwarded this, however: (1) You need a metric default outside of the US. (2) >4 shelves does not work. (3) 'Other' hardwood type not possible. (4) Could not find a way to get chamfer to render on slab top.
can not answer to the other points. But under 'set up shop' there is a selection of metric vs imperial units. (among many other things)
I get it, but most of the world will find that annoying. Hence, intelligent default.
I use metric as a default in the US =)
FUTURIST! Love your style. I hope you also adopt YYYY-MM-DD ISO dating.
Having just gone on a tear about why everyone should make their own shop drawings, I have to say that this is really well done. Nice work on this, and good job on incorporating some really good, practical woodworking knowlege.
I try like hell to stay out of the business of plywood boxes, but they're inevitable sometimes. I'll try this out when I have a project it's a good fit for.
This looks very nice. I can see how opinionated it is in a way that it suits your needs well. Cheers!
As an engineer obsessed with the finer details and getting his fix from weekend woodworking by making things just the way I want for fun, and tinkering with newer ways of doing things, some finer details that probably won't make a lot of rational sense, but I really badly want them because it is cool.. I want a more general purpose workflow where I can make anything I feel like... {}toys for kids, bike stand for the shed, A tool wall, Bed for the kids..}. Your approach to doing what you happened to need - bookshelves, workbench etc in a customisable way is very cool. But, I've already made those over the years and need something else.. :-)
Your work gave me a lot of ideas and levelled up what output I can make once I figure out a more general purpose workflow.
ShopSpec looks interesting. I looked at the shoe bench in the gallery, and I see in the 3D drawing there is a finished top piece that overhangs the bench underneath. That part doesn't seem to be in the cut list.
This is amazing -- I was looking for a tool exactly like this to DIY a bookshelf. That said - I noticed none of the patterns had curved edges (or curved sides e.g. for a corner bookshelf. Is that technically possible or out of scope for now?
I’ve started doing some furniture design in CAD and I’ve been wondering how people model plywood. Do you make 3/4” plywood 0.75” thick, or do you use the actual sheet thickness (often, but not always, 23/32)?
Am a furniture maker, professionally. Do mostly hand work or at least more traditional tools, but use CNC with some regularity for jigs, templates, and the like.
If you're CNC cutting parts that need to fit together, you need to measure both your plywood and your cutting tool with digital calipers to the thou. Freud's 1/4" upcut spirals (available at Home Depot) are pretty commonly .245" rather than .250". That's enough that things don't fit.
Yes, I've been burned by this.
Also, if you're just making through cuts on your CNC, reference the bed for the Z-axis rather than the material surface, and a few thou either way doesn't matter.
I'm not even thinking about that kind of precision work.
For a basic bookshelf, the space might be constrained. Say I need the outside dimension to be 24.5" wide. If I'm using 3/4" plywood, do I model it so I have 23" wide shelves or 23-1/16" wide shelves?
Or is it irrelevant? Do you build the box first, then measure and cut the shelves to fit?
The more I think about it, the more I'm concluding that you use 23/32" and then do a lot of measuring and adjusting as you build. Taking a cut list and cutting everything ahead of time is probably a bad idea unless you know your plywood is exactly the right thickness.
In most applications, it doesn't matter if the piece ends up 1/16" (1.5mm for the rest of the world[0]) undersized and I wouldn't worry about it. If for some reason the finished piece had to be 24.5" wide, I'd account for the off-nominal thickness of the plywood and charge more for the hassle of it :-)
Generally though, if you're putting something into an alcove and want a fitted look, you'd build the box undersized by some amount (1/4" to 1/2" depending on how square and plumb the walls of the alcove are), set the box in place, and then scribe a face frame to the walls.
Drawer boxes tend to be where you have to work to the tightest tolances. Side mount drawer slides don't have a lot of allowance for the drawer to be undersized and basically none for it to be oversized. Under mount slides are a little more forgiving, but I definitely still account for my actual material thickness on them. In either case, you're definitely building the drawer boxes to the as-built size of the opening they're going into and not the platonic ideal opening from the plans/drawings.
[0] Yes, I know. Slightly more than that, but this is woodworking tolerances.
> Side mount drawer slides don't have a lot of allowance for the drawer to be undersized and basically none for it to be oversized. Under mount slides are a little more forgiving, but I definitely still account for my actual material thickness on them. In either case, you're definitely building the drawer boxes to the as-built size of the opening they're going into and not the platonic ideal opening from the plans/drawings.
This doesn't work great for what the previous poster is asking about, where something needs to fit into a specific space (the comment about scribing a face frame is mint though), but what I typically look for when I'm building things, whether wood, metal, 3D printed, etc, is to try to find the critical faces and let everything shake out around that.
For example, in the side-mount-slide drawer box situation, you've nailed it: the spacing between the exterior face of the drawer and the interior face of the carcass is critical. What I personally would do for that situation would be something like:
- cut rear carcass rails and drawer front and backs precisely with exactly the right spacing, and probably a few temporary front carcass rails that won't be part of the finished product but can be clamped in place for lay-up
- the drawer sides and front/back get dowels that are drilled referenced to the outer edge of the drawer front/back and outside face of the drawer sides
- a slightly oversized dado in the drawer front/back/sides so that the bottom doesn't need to be made as precisely. It can still fit snug in the slot, but if it's a little oversized or undersized relative to nominal, it's not the end of the world
I checked this project couple months ago and i can say it's really nice! Definetively worth checking!
This looks really nice, I'll give it a shot with my next project!
I want to self host this. Where’s the code?
This looks fantastic - great job!
This is so clever.
why does this need to be a website?
I build furniture professionally. I mostly do commission work, and largely for people who are remote to me, which means I exchange drawings with clients digitally, usually in the form of a rough render (no wood grain texture applied or anything like that) out of SketchUp or FreeCAD[0].
When I actually go to build anything, I generally do pencil and paper shop drawings, usually 3 views, hidden lines showing joinery, etc. I'll make exceptions for simple projects, but for anything even moderately complicated I do shop drawings. "Moderately complicated" starts at a side table with a drawer, and that's something I've put together more than a few of.
The important output of the drawing process isn't a picture of the finished piece. It's knowing, deeply, how all of the pieces are going to fit together and how they relate to each other in space. It's having an order of operations and assembly in mind. It's knowing where the pain points and hiccups are likely to be. It's a good cut list with notes about e.g. what the shoulder distances are for anything with a tenon on both ends.
I don't doubt that you could accelerate the 3D modeling process with AI or a sufficiently friendly CAD program, just as you could take plans from Fine Woodworking or Popular Woodworking and go directly to the shop and start building. I do doubt that things would go faster or more smoothly in the shop for having done so.
[0] Which depends largely on the complexity of the project. This gossip bench was simple enough to do in SketchUp:
https://www.longwalkwoodworking.com/gossip-bench
This dining table required some serious leveling up of my FreeCAD skills:
https://www.longwalkwoodworking.com/mid-century-modern-table
My experience is that if there's a lot of shaping with curves and tangency, FreeCAD is less cumbersome to draw it in and a hell of a lot easier to make changes in.
A little bit unrelated, but I was wondering if you could give any advice on how to better mentally train your mind to understand order of operations and assembly better. Is it just a matter of conscious practice, or is there some technique? I love taking things apart but putting things back together seems to get harder and harder, especially as devices get more complex. I've always wondered how I could do better in this manner, other than taking photos(that end up not being useful), of the disassembly process and hoping I put things back together properly.
Uh, I spent a lot of time playing with Legos as a kid, but if you can find a time machine, there are probably a lot of way more profitable ways to put it to use than giving your past self some Lego sets.
If I'm taking apart things on my car, I'll do one side at a time even if it would be more efficient to do both at once so I have an un-monkeyed-with side for reference if I get confused putting it back together.
I tend to stay away from taking apart and reassembling electronics; I can't fix anything inside anyway unless there's an iFixit guide that I'm blindly following.
Most furniture projects break down into at most three (or thereabouts?) hierarchical steps for any single assembly. Which is to say, my spatial/assembly skills probably aren't actually that developed via building furniture.
Which is to say, great news if you want to build some furniture! Pick a simple project and wade in!
> https://www.longwalkwoodworking.com/mid-century-modern-table
The leg/stretcher joint you zoomed in on at the bottom is immaculate. Wowza.
I've done enough woodworking to know how difficult that is.
I also love the bevel under the top. Kudos, all around.
Thanks! The three-way joint where the stretchers come together is wild too. It's a three-way finger joint (for structure) with a three-way miter on top (to get the profiles to come together nicely). Drawing it is one thing, and cutting it is a whole 'nother thing :-D
The beveled profile on the top was the clients' touch. We went through four or five iterations on it. They have great taste and are a ton of fun to work with.
I'm in the middle of ginning two prototypes of a chair meant to go with it. It's as yet unclear if I've made my life any easier than the table or not.
Is it possible to learn something like this later in life? My granddad was a carpenter and had a shop but by the time I was a kid he took up drinking pretty heavily and I barely saw him working. I suck when it comes to mechanical work or something similar but I think I'd enjoy working with wood.
This was a career change for me; I somewhat infamously no longer build software[0]. I went back to school in my thirties to learn furniture making. I had never picked up a hand plane or chisel prior to taking classes. I started with some evening and weekend classes, followed by a couple of weeklong classes before applying to go to school full time.
As with learning any skill, I'd suggest finding a project to work towards to motivate you.
I was fortunate to have two full-time programs to apply to in the Boston area (now one, sadly). The biggest difficulty for finding training is likely going to be finding a place that offers it.
New England has the North Bennet Street School, the Center for Furniture Craftsmanship, Vermont Woodworking School, and maybe a few others. As I'm currently in Vermont, I know the New England scene the best.
[0] https://news.ycombinator.com/item?id=24541964
Your gossip bench reminds me of some of Alan Peters' pieces, not surprising given the Arts and Crafts style requested by your client and your obvious attention to detail.
Such beautiful work, thank you for sharing.
Thank you!
Excellent work!
Thank you!
OP here. writing for my own reference. Found great pointers so far.
I'm going to try https://sawdust.diy and https://fluidcad.io/ for the short term.
For the long term, I have noted FreeCAD + Blender + $ai_model to be a good general purpose workflow that yields more control, and will probably get me lost into the details.
https://janne-alatalo.fi/en/articles/silhouette-modeling/ and its accompanying SKILL - https://github.com/janne-alatalo/image-to-cad-skill
FreeCAD MCP: https://github.com/neka-nat/freecad-mcp
Woodworking specific FreeCAD resources : https://github.com/dprojects/Woodworking
Two YouTube Channels related to FreeCAD + woodworking :
1. https://www.youtube.com/@dprojects.woodworking
2. https://www.youtube.com/@ga3d_._tech528
There goes the weekend! Cheers HN!
A friend of mine was borrowing the shop of a very well known luthier to build some furniture. I stopped by to check the whole situation out and I found them both with their brows furrowed trying to work out some tolerances for a joint on a scrap piece of paper. As an architect by training, I quipped "at some point you'll have to start making proper drawings of you projects ahead of time", to which the luthier replied "the plans are always the problem, you're better off letting the wood tell you how it should be put it together." to which I had no reply..
Having recently had my bathroom done, I was surprised to see that none of the trades had any kind of drawing or preparation; everything was eyeballed together. Slightly less surprised when there was a catastrophic measuring error.
I have a lot of respect for the intuitive-improvisational mode, and some people can do it brilliantly while playing the violin, but I'm not sure it always works for making things.
My personal experience is that woodworking at hobby grade is a art+science+engineering in varying proportions depending on the person's interests. I can relate to your friend in that almost always, as I work through a project, it evolves in its details, joinery, design (even size as I make my mistakes) etc. However, it is important to visualise _what_ one wants in mind before beginning to mill wood. I sketch so much in various perspectives to narrow that down and try to visualise how my idea would materialise.
If AI could catalyse that first part and help visualise the idea in many perspectives that are easy to tweak and improve, I think it will be a solid base to work upon and change organically as we build it in the shop.
As an amateur wood worker, the main issue is that I can’t cut things as precise as I want. It’ll be a couple mm off, or slightly crooked, or I’ll have cut too much and need to find something to fill in the blanks.
You may call that the art part, but it’s actually the terrible skills part.
I'm with you brother/sister! I recently acquired a small hobby-grade laser cutter that can do 1/4" plywood happily and 1/2" plywood if you ask it really really nicely.
One of the things I intend on doing with it is cutting router templates for parts that I need to make a bunch of with "identical" dimensions. Get it as close as I can with the table saw and miter saw, stick the template to it, and use a flush-cut bit to clean up my slop.
It's a fun tool in its own right, I really get a kick out of designing and cutting tab-and-slot designs. They just fit together so beautifully right off the laser. I get the joy of designing the project and assembling the project without the swearing/frustration bit in the middle.
The grandfather of one of my son's friends was a locally-noted woodcarver --- when his daughter first brought home her future husband, he handed the prospective son-in-law a piece of wood and a knife and asked, "What do you see in the wood?" When the reply was, "A piece of wood.", he took both back rather disgustedly.
His woodcarvings were _amazing_, in particular for his ability to work with the grain and even to chase a single ring so as to make a perfectly shaped, but seemingly impossibly thin and light wing of a bird.
I'm a developer and hobbyist woodworker too :)
I'm also the developer of FluidCAD. It has an MCP you can wire to any LLM. It runs locally on your machine.
It is still missing features for splitting the model into parts, but that is coming in a future release.
https://fluidcad.io/
MCP config (node.js required): https://fluidcad.io/docs/cli/#fluidcad-mcp
FluidCad looks smooth. How much AI generated code (%) is used in FluidCad? And how long did it take to make?
I have started tje POC 2 years ago without AI. When it reached a shape I like I started using AI. Now all code is AI written but I'm still controlling the overall architecture.
This looks really cool! Nice work
Shameless plug: I’m workin on http://partforge.ai right now it’s mostly aimed at 3d printing but it can create laser cut sheet parts with dxf file exports and will support cnc routed parts with drill holes and socket diagrams built in in the near future. Board cut lists as a export is a little further out, but you can ask it for measurements of anything you build and it would probably be a pretty useful tool.
Just a little feedback: one of my most hated dark patterns in design is when you give the user the impression that they can try out your website but they actually can't. That's the case on your website: there is a text field making it seem like you can give your site a spin, but as soon as you hit the submit button, you get a pop-up telling you that you have to sign up first. And that after I already spend some (admittedly small) effort to craft a sample text.
I personally hate that pattern, and my default reaction is to immediately close the tab.
Perhaps you could change the landing page to avoid that negative first impression?
Claude Code is now WAY better at the freecad python api. My product (related to ceramics) does a whole bunch of custom 3d modeling and the new generation of LLMs can go in and make significant changes and basically get it right. They can also deal with a lot of annoying corner cases when you run into them.
I've also had really good success with FreeCAD, and the FreeCAD MCP server. So far I've had it design and build a custom workbench (woodworking project w/ cut list, assembly and hardware instructions, tool and part check lists) as well as a omni-directional differential style robot wheel module for a 3D printing.
I will say the differential wheel module was on the edge of what it was able to do. I had to bump it up to Fable and if I didn't already have a clear model in my head of what I wanted I don't think it could have pulled it off.
How do you prompt it? It seems it would be difficult to describe a 3d geometry correctly just with text. Do you provide hand-made sketches?
All text, but none of these were a one-shot task. There were a few serious gotchas that you need to pay close attention to. It understands problems VERY well when it actually controls the viewport and takes screenshots of the part, unfortunately it REALLY resists that instead preferring to make up a bunch of equations to justify/validate it but these were almost never correct. It frequently got things like axis backwards so when it would test for a potential collision it would test in the wrong direction. Guidance specifically for the axes might help there, I suspect it's assuming different real-world axis (maybe more aligned with the game industry axis than modeling or CAD axis standards).
When I approached those two projects I took different approaches. The workbench I had clear measured physical requirements and desires but no specific design in mind (such as number or size of drawers). I had a long back and forth working out a purely textual project description via Fable chat, I originally wasn't even going to model it in CAD and just build from the textual description. I had just seen someone else post success with FreeCAD + MCP and there were some measurements that were suspect... So I had it model it. It did pretty good entirely on its own but a wood bench is composed of effectively a bunch of differently sized rectangles oriented and put together correctly so it feels like this was an "easy task" for it to complete.
The other side of the coin was that inverted differential omni-wheel. This one I knew mechanically exactly what needed to happen and I wanted to model to make a parametric, re-usable model that could be dropped in to a bunch of different designs. This one needs some complex gearing built which it actually mostly did pretty well. Where it kept failing here was weirdly in the motor placement (it was a stock placeholder mesh of the motor part), it had a sled mount with screw slots to allow a little adjustment of the meshing of the final gears. Over half of my time working with the model was simply trying to get it to point the motor model in the correct direction, fully seated in the sled, with the screw slots accessible and physically not colliding with anything. The next hardest part was composite/boolean joined parts, specifically a couple of gears that are a combination of crown and pinion gear, it couldn't seem to comprehend that adding the two physical objects together wouldn't remove excess material from around one of the sets of teeth.
Kind of a ramble, but let me know if there are any more specifics I can provide.
Which freecad MCP are you using?
This is the one I've been using: https://github.com/neka-nat/freecad-mcp
In my experience the MCP is not needed, it just runs headless FreeCAD using CLI. The MCP can be useful if you want to run FreeCAD on a VPS, and then use ChatGPT e.g. on your phone (optionally via voice). But for local I'd go with the CLI. But they'll do just fine with the MCP, which probably wraps the Python API anyway (ideally, otherwise it could lack some features).
OpenSCAD as well. I bounce back and forth between the two of them a fair bit depending on what I'm doing and which one's going to be more ergonomic for the problem at hand. The Fusion 360 built-in chat thing... not so good in my very limited experience.
Seconding openscad (havent tried freecad to be fair) with opus 5.5
I had it design a model sailboat hull, and it fucking nailed it. It even designed it for printability. I’m genuinely really impressed.
I can imagine. I did a bit of poking with blender and the api use got better there as well. For my use case I needed BREPs so stuck with freecad. I'm tempted one of these days where I have a pile of extra tokens to see about converting it to directly use the Open Cascade library since I just need to model and not the UI.
Second this. Since Opus 4.6 there's been a very noticeable bump in accuracy at just doing FreeCAD+Python or OpenSCAD code, usually one-shots things with basically described geometry.
Recently, Sonnet 5.5 got quite good, too, but not at the level of Opus/Fable for complex geometry
Disclaimer: I use it for very precise 3D printing, not woodwork.
I'm now printing my 3rd or 4th totally Claude-generated 3d printed custom project enclosure. Opus 5.5 is quite good - it's been generating CadQuery scripts and exporting them as STL for me, along with image previews and so on.
Give my tool a try, https://sawdust.diy
Great work.
The UI styling looks very similar to the other website mentioned here
https://shopspec.io/
Just a coincidence or is there some collaboration already ?
We haven't collaborated at all but are working on very similar projects, so probably do think a lot alike. I last checked shopspec out when the creator mentioned it in the thread[0] where I first shared Sawdust. I just took a look and it has definitely grown in a similar direction, but I certainly wouldn't attribute that to anything aside from similar people working on similar projects and communicating with a similar visual language.
[0] https://news.ycombinator.com/item?id=49234277
Maybe they used the same LLM model
I have been beating my brains out trying to make a deck base come together in my brain, this is very interesting. Thanks for posting it
That's exactly why I built it, I needed my brain visuals to match reality a bit more when building a shed. Curious to hear how it goes! If you run in to any issues please ask your agent to send in a feature request/bug report, or drop me an email (it's in my profile).
Hey. This is very cool. I will definitely try this out this weekend for the projects I have in progress.
RapidCAM.app (https://rapidcam.app) has excellent support for AI. The file format specs are published and open source so AI can easily write an ".rcam" file.
RapidCAM.app is a parametric 2.5D CAD/CAM for CNC and laser with support for rotary axis. RapidCAM.app runs in the browser or as desktop apps. There is no login required. The app is free to use. Privacy is respected. rcamhub.com is the sharing site for .rcam files.
Within the App, you can define your project and then use the built in prompt generator. This creates a prompt with all the details AI could need. Once the AI replies with the file, you can paste it back into the app which will then verify the file for you.
Desktop versions of the app have MCP server built in so AI can control the app directly if that is a route you prefer.
I started RapidCAM for my own use as I found that the CNC was sitting idle simply because firing up a full CAD/CAM package took too long. The idea with RapidCAM is that you can quickly sketch out your job from as simple as you need to as advanced as you want going from unconstrained to full parametric/constrained as required.
I'd say Claude/Codex plus whatever CAD modeling tool you want to use. But if you want to find some existing AI-assisted CAD design platforms, take a look at https://thecadhub.com/category/ai-assisted-design/
Why ruin the fun of a hands-on project with computers? I'm also a hobbyist woodworker/DIYer and enjoy the drawing aspect, thinking through the space, the dimensions, etc. and drawing that out with pencil and paper. Its relaxing and by nature disconnected. I'm not on the clock and trying to build things for customers so speed isn't necessary. The level of accuracy in software is thrown out the window when you start dealing with actual wood that has grain, knots, different sizes, etc. I find myself making adjustments in the shop as a project progresses where fine measurements on paper are mostly useless.
I would argue if you're building plans to make a lot of repeatable items, then you're beyond hobby level.
I understand the sentiment... As a computer engineer who enjoys woodworking because it is tangible, abstraction-free, and in full control right in front of your eyes, the line I draw is not "I won't allow computers into this Zen wood shop". Instead, I use computers to accelerate the error prone parts of human planning, and also expand my cognition by making things visual beyond simple imagination. If I see that Coffee table proportions I had in mind as a CAD model, I may spot any balance issues, and even validate if that is what I was going for aesthetically. Heck, it might even give me a chance to improvise on the design because I have now visualised it outside my mind.
Once the CAD model validates my idea, and gives me a rough plan, the zen part of working with the wood, adjusting for grain, knots etc can begin. Even while making changes on the fly, a visual model of the original plan comes in handy.
I tried this for my workbench a few years ago.
https://aravindh.net/wood.html#gallery-7
https://aravindh.net/wood.html#gallery-8
and it significantly helped without removing the joy of making mistakes..
I'm not a zero computers zen wood shop person. Just offering a perspective based on my experience. I've also built from others digital plans and my own and find that for my workflow, the higher fidelity doesn't add much value. Maybe its a personal tendency to try and make it pixel perfect and because of that I sink way more time into it than I should. Pencil and paper help me avoid that rabbit hole for woodworking.
> a personal tendency to try and make it pixel perfect and because of that I sink way more time into it than I should.
Now that resonates too close to home...
May be I will come to the same conclusion as you after spending hours/days/weeks into trying out a bunch of things with CAD. Lets see... this rabbit hole feels worthy of jumping into.... (it will be different this time!)
Why judging when someone prefers a different way to work than yours?
I've tested different ways to use agents to model stuff from images with accuracy. Maybe this is something that can help or give you ideas: https://janne-alatalo.fi/en/articles/silhouette-modeling/
If you have some physical reference, for example a coffee table, you can create an accurate 3D model of that quickly. The agent creates model that can be converted to STEP format and opened with any CAD software.
This might help you? You get a good model that you can start editing towards your own design.
Here is agent skill that works with OpenAI models and Codex https://github.com/janne-alatalo/image-to-cad-skill
Basically you take few pictures. Three is usually enough of furnitures. The agent uses the pictures to find the exact camera poses and creates a 3D model that minimizes the difference between the object's silhouette in images and in the 3D-model when projected with the virtual cameras to the 2D planes. The agents create the model with python scripts. First using numpy for faster optimization and finally CadQuery for easy exports to CAD formats.
OpensCAD and FreeCAD.
I learned OpensCAD manually but it was so painful because you needed to take into account the most minimal and ridiculous thing using code, so I used Freecad in the end that is way more intuitive and fast with graphical tools.
With code like OpenScad it was just too exhausting just to have to think rationally every single detail. And you spent hours doing the most minimal project.
Then LLMs appeared...
Now I use OpenSCAD a lot because with LLMs you have the absolute control that code gives you without the pain of using your logical/rational mind all the time and taking 1/20 of the time for that.
I create my own furniture as hobby. Mostly I use standard IKEA metallic pieces, standard metric screws.
I generate paper blueprints automatically of how the wood panels must be cut and they cut it for me. My Blueprints are pdfs that I print very similar to IKEA blueprints so the one that cuts the wood can not make a mistake. I choose and provide the panels myself.
It is ridiculous how easy it is now with LLMs to do all of that. I can do a new design in a couple hours, including the pdfs. Most of the code is already created and I just have to reuse it.
I use Claude Code. From time to time I voluntarily teach children to do just that. Some of them are really good after a couple hours of instruction and some mentoring.
I've had poor luck with LLMs in OpenSCAD. They seem to struggle same as I do. The relatively long rendering times are also off putting. Unfortunately, in my laziness, I've locked myself into Fusion for now, but I do quite enjoy modeling by hand in it.
I started my woodworking journey about 8 years ago and have kept improving over the years. checkout my insta - https://www.instagram.com/rakas_woodworking/.
My curiosity lead me to down this rabbit hole as well. Freecad with the woodworking workbench helped me create my plans initially. Since, have moved on to claude code and Freecad to create python scripts to create and modify my cad drawings. A few things which have been able to incorporate in my plans is to have a 3D design, cut-list, shop drawing for joinery and assembly.
Am working on a workshop designer module with chat interface and freecad sandboxed mcp with a support of multiple LLMs. The goal is to take a paper drawn design and have the system build the cad drawings, cut-list, shop drawings and maintain multiple versions. The challenge is all wood working projects are unique and need different approaches. Trying to resolve this by creating skills - building cabinets, building drawers, framing, etc.
Loved all cool ideas out here and it is good to know that am not the only crazy one out there. Happy building folks!
Here’s the video of the prototype - https://www.instagram.com/reel/DekB279KMIR/?mdxt=MW5ydDlpOHd...
I'm a developer and a previous commercial concrete superintendent. I built a 3d model designer similar to Autodesk Revit as well as a pdf editor similar to Bluebeam. You can connect MCP to it to build full buildings based of drawings.
https://builder.auxx.ai/
Everything is stored locally (with cloud feature coming soon as well as desktop versions.)
I recently used Opus 5.5 to diagnose and discover a certain (niche) cleartext format CAD file. Also for generating small, new CAD files containing a small model for test purposes. All with satisfaction.
Coincidentally, I also seen a (private) demo using GPT-6 Astra designing wall panel joints based on some pre-determined rules, 2D lines specifying the layout, and later altering the design following a hand sketch (photo of a sketch). That looked promising too. It was claimed that spatial reasoning of Astra is elevated, can work well with 3D models and formats.
None of those are production (something to manufacture) level just yet. But if I had time I'd explore this manipulating CAD files by an agent route, opening those files in the usual tools I have at my disposal.
Talking/chatting about 3D is like dancing about architecture in my view, so I think this LLM use route is not sustainable straight, still, my above casual encounters suggest, for simple things, combined with manual adjustments, it may be alright.
I’ll share a story. I wanted to make dxf files for some decorative metal gussets I needed for a project. I find CAD programs unintuitive and tried to use Claude as a tutor. That was a fail, it seemed to assume I was more knowledgeable than I am. So then I tried to describe what I wanted and have it emit python to draw it. Again a fail, it didn’t interpret my descriptions accurately and lacked aesthetic sense. Then I had Claude implement a simple DSL that captured my sense of the geometry and form I was trying to express. I ended up wth a very bespoke Logo like language that did exactly what I wanted. I believe there’s a larger lesson there in AI interaction.
Be aware that AI is really bad at certain kinds of geometry. This can either go very well or very poorly. I'm not aware of many happy cases in the middle.
A simple test is that if the object you are modeling could be described by a brief python program (automating blender/CAD APIs), then the LLM will probably one shot it perfectly. If what you are modeling is a human face or bird, then the LLM is at best a clumsy apprentice. High Kolmogorov complexity is the common thread behind all things that LLMs will struggle with.
It can sometimes be easier to lean on a diffusion model and then trace over the results the old fashioned way. Diffusion completely sidesteps the geometry which helps with design speed.
From https://news.ycombinator.com/item?id=36191589 :
> tsugite
> compas_wood / wood_nano
clementzheng/joinery: Parametric joint generation toolkit for laser cutting: https://github.com/clementzheng/joinery
GitHub topics: joinery, woodworking, CNC
Though, there is 3d printing of wood now.
And here's a wonder material: Lignin-Vitrimer with Lignin-Derived Carbon Fiber, and Cellulose
For realizing designs in physical space, I create a Python library with a DSL that allows us to express all of the components and how they relate with each other. The most important thing this provides is a deterministic way to test the assembly. Then, you take the parameterized relationships between the components and export them into things like three-dimensional views or cut lists, rather than trying to manipulate three-dimensional software as your source of truth. (Although Claude is pretty effective at driving Blender via Python, too.)
Sounds interesting!
I've been working on this sort of thing at a far lower-level (directly modeling toolpaths and tool shapes so as to get 3D models of parts).
PythonSCAD has an Align command which I need to wrap my mind around to see if it would be workable for positioning parts.
I’m doing exactly this (in TypeScript) for buildings / construction. It can’t really do woodworking (not designed for that) but I can confirm that it’s an effective strategy for spatial assemblies.
Out of curiosity, is this a self-directed (business) project or are you employed somewhere? What types of buildings and assemblies?
Stealth-ish startup right now (https://bear.build) but we’re working with some large contractors to develop the product. Assemblies are nested and go from a corner detail through walls or MEP systems to levels to the full building being the ultimate assembly.
sounds indeed interesting. can you elaborate on what information your DSL expresses ? is there a solver which calculates the actual metrics?
Cabinetry stuff is still rough, but here's an example of the methodology applied to PCB layout: https://github.com/tcdent/netspec
For 3D printing, I just ask Claude Code to use text based 3D modeling software, and to build a directory tree per project (with make to convert to something the slicer can use). I’ve printed non-trivial projects this way (60 parts) without trouble. Be sure to ask it to parameterize the models and put the parameters at the top.
I imagine this would work just as well for CNC wood carving/routing projects, and maybe even for complex assemblies.
Onshape, like Shapr3D, is based on Parasolid and works on desktop and mobile. They added MCP support a few months ago and there’s a lot of people who use it professionally for cabinetry etc. Even before they added MCP support, the way everything can be customized through the FeatureScript language has led to libraries of custom features for woodworking. If everything you’re working on is for fun (non-commercial), your Onshape license is free.
For those of you interested in building 3D things (using CNC, lasers, woodworking, 3D printing, etc), check out this forum:
https://forum.makerforums.info/latest
There are some active HN folks who participate in both communities. (Check out Oscar Gallegos, who uses AI to generate depth maps, and carves those into wood using CNC router)
Might be worth a look at https://openscad.org/ which is a free tool which designs in 3d based on a programming language that LLMs find easy to use. Then https://cutlistevo.com/ for optimization and nesting of your cut list.
I had been using Gemini to build OpenScad models. The other day Gemini mentioned CadQuery as an option. It's essentially OpenScad for Python. The big plus is b-rep modeler.
https://github.com/cadquery/cadquery
crosstrees.1puni.com, mostly built from my phone while hanging out in her saloon!
For you specifically; if all you want to do is manually have a session and describe the thing you want, and see it take form — that's OpenAI's expertise. Pay 20$, get the desktop app, tell it what you want with as much precision as you can. Don't tell it how (don't force CAD if you don't specifically need it). Give it pictures or a photo of a drawing, any data like wood type, maybe even the machines you have at hand... Just dump it all in there. You'll be amazed.
Anyway, I'll plug India, the boat I've reconstructed and had the absolute privilege of helping design the rig for. So that's my weird hobby that AI helps with... rigging Pirates of the Caribbean-style boats.
(Yes, we actually sail them in our community. There was a race a couple of weeks ago. India's yet to be rigged, so she just tagged along as a fender against the cliffs.)
Not yet fully baked, but I am planning to add a woodworking mode to claydash with natural cutting UI - For now I have a couple of wood materials and there is the ability to extrude + cut faces à la sketch up, which should work for simple projects.
The local version has a MCP server.
see https://claydash.com/
Probably just me, but app.claydash.com doesn't seem to work in FF.
I am a woodworker mostly but do it all on pencil and paper. That said I have a 3d printer and cnc and fusion360 with the Claude mcp connector has been pretty amazing in my tests. One more year and it will be a new world.
I have gotten just "ok" at CAD. I'm not as productive as I should be because I avoid it. Really looking forward to this.
I second Fusion with Claude via MCP.. works pretty well.
Astra in Codex CLI is good with FreeCAD if you let it use the FreeCAD Python runtime in a headless session. It is good at relying purely on natural language to design and revise. To follow specific CAD techniques you need additional prompting. Highly recommend. Uses quite a lot of tokens.
I do home improvement projects (I've in wall built-in storage, benches and nooks) I am on a clock and i have very little room in which to work. The only tool I have relied on https://www.cutlistoptimizer.com/ I have found that the CAD based tools to be pretty much beside the point for _most_ wood working projects for hobbyists, for a few reasons:
1. First several 3-d design iterations are throwaway reworked because I am constantly measuring the design, clearances and studs. And paper works best here instead of working with clankers which takes way longer.
2. Choosing the right kind of materials: thickness and type of plywood, type of hinges, panels, finished or unfinished. Optimize for simplicity of putting components together is most important.
3. Once the design settles the actual joinery needs to be as simple and efficient e.g. butt joints work well most of the time. A good jig for pocket holes is generally the most needed. You will be surprised how well a staple gun works for creating back panels of cupboards.
Its not that they are not useful, shopspec looks great(good job variodot), its just that I can get further and faster without them for most hobbyist pursuits. I invoke YAGNI most of the time because I constantly ask myself one question: "How can I make this be less time consuming?".
Hey! ShopSpec has a standalone optimizer too separate from the parametric design. Check it out and let me know any feedback - https://shopspec.io/cutlist
I’ve been using an llm to generate both renderings of furniture and the gcode for it to be cut using a cnc and assembled ikea style. One off custom furniture at scale.
I use a combination of openscad, blender to render previews of the full thing, and opcut to generate cutlists. I usually ask the models to generate a workshop pdf with the cutlist and the exploded view of the assembly.
I'm doing mainly simple furniture and cabinets.
Shameless plug since I work for them, but have your tried Vizcom? We're in the ai-assisted prototyping and design space. Our focus is industrial design but I don't see why you couldn't get assistance with woodworking projects. :)
Wow i was just thinking the same thing. Going to take a cbc course at my local shop.
Does anyone know what the SOTA is for cad models from image or multiple images?
I was hoping to try doing some reproductions of stuff i saw in museums/palaces in Europe.
I’m using Plasticity with an MCP and Astra for 3D printing work, haven’t tried it for woodworking projects yet. It’s decent at modeling medium complexity enclosures and structural supports, so might be worth giving it a try.
Also a hobbyist woodworker. I have had both Claude and Gemini generate files I could open in openscad. I mainly use them to generate STL files for 3D printing but I bet it would work for woodworking as well.
I am not a woodworker but wanted to make a simple dehydrator and had good results getting a cut list and build steps with pictures from Claude and the Sketchup integration.
At what point is it no longer being a woodworker? Ai does the design and the modeling work. A robot actually does the cutting.
Isn’t this closer to being an architect or a designer now?
The line has always been blurry..
Why use power tools(planer vs hand planes, power saw vs hand saws, saws instead of chisels etc) when you could do things by hand?
It’s all about which parts one enjoys doing by their own and which ones they’re willing to abstract away with a tool.
Some folks abstract away the whole process and just visit IKEA :-)
AI makes it easy to build the first thing that comes to mind.
When was the last time your first idea was the good one? Mine certainly never are
Since relevant community is here - what are some of the good online resources to learn woodwork? What tools/power tools one needs to know specifically?
You really need to build things to learn and progress. Woodworking for Mere Mortals youtube channel is a good place to start. Start with hand tools and build some very basic things, see what you like doing and progress from there. The caution with all online content is the constant promotions, etc. for recommendations of tools or brands. Look for counter opinions. See if you can go use a tool somewhere before buying, maybe at a local store like Rockler or Woodcraft - they may have classes. What you won't see in online content is how long something really takes, they are probably editing 40 hours of video down into 30 minutes.
In my experience, a track saw is immensely more useful than a simple circular saw or miter saw for finer woodworking or cabinet work. The other two are great for rough carpentry but tend to be harder to use for finer tolerances needed for finer woodworking. They are more expensive but because of the track you will get straight cuts with little setup. I've had issues with a contractor sized table saw even with it built into and secured in a DIY cabinet. Lifting and moving large sheets of plywood or assembled boards like a table top can be prone to more errors than setting up and moving a saw along a track. Really expensive table saws are probably better but as a hobbyist I don't have $3000 for a single tool.
90 deg corners... Get a square that you trust. Learn the 3-4-5 method.
patience.
Wear hearing protection.
You more than likely will probably never need a table saw, jointer or a festool domino tool.
Tools I'd get first:
- japanese pull saws
- good chisel set
- a track saw... and a 2.4x1m.2m sheet of foam to cut on
- a palm router, learn how to make all your own jigs
- 12 irwin quick clamps. if you also prefer and can afford, 12 t-track f clamps.
- an impact dril, and a normal drill
- a decking drillbit
- a marking guage
- pencils
- a speed square
then
- make or get saw horses. and 2.4mx1.2m sheet of formply
100% avoid:
- 90 corner clamps.
> You more than likely will probably never need a table saw, jointer
Very much depends on available material. If you do have decent square boards or plan on mostly using thick plywood, then yes, you can make a lot of practical stuff easily with miter saw and an improvised track saw, or just a real track saw. Otherwise, you'll want to have a jointer.
The necessity of a table saw is a controversial topic, a lot of guides position it as the only saw you'll need, and while technically that may be true, it's way less safe and an overkill for simple projects. Also, expensive in both money and space, since this is a tool you definitely don't want the cheapest and smallest version of. So I agree with you here. If I had the current experience, I'd get a decent track saw instead of the miter saw, more versatile.
I'd prioritize a router table made with a basic wired trim router and a cheap adjustable baseplate, with dust extraction.
I've had good results with Claude Code + OpenSCAD.
https://sawdust.diy/ uses LLMs for wood designs
Hey that's me! Thanks for the plug.
I used blender mcp and Astra to do a woodworking design a few days ago, plans came out great.
Model wood with AI? How are you going to carve it? Which machine?
Ask Claude to generate OpenSCAD files.
Model wood? How are you going to carve it? Which machine?
I use blender
zoodev?
[dead]
[flagged]
[flagged]
[dead]