Use an agent to draft parametric geometry systems
A Rhino plugin let a coding agent turn a brief into editable geometry logic stored alongside the project files.
- What they did
- Miro Bannwart connected his Rhino/Grasshopper plugin to an external coding agent and limited it to a saved project folder. The agent started by asking about the design goal, then created linked Geometry Stations and wrote their code and inputs into text files. Miro reviewed the canvas and adjusted the parameters; in one test, they annotated a screenshot with red and green marks to fix a staircase handrail.
- How it went
- The setup produced examples including a chest of drawers, a curved staircase, a villa, a bookshelf, and a timber frame. It is still in an experimental alpha stage. Miro got the best results from GPT-6 Astra, and local-model runs failed.
- Tips
- Keep the agent boxed into the project folder, and save backups before testing. Begin with a small model, and be careful with IFC export because reimport can fail and the export can take minutes.
Try it yourself with Claude Code
I want to make a parametric model for [object or structure] using [Grasshopper / CadQuery / another modeling library]. Start by asking the smallest set of questions you need about the form and the controls I want. Then build the system in [project folder path], and store the code plus each input value as text files next to the project. Show me the result and wait for my approval before you send, export, delete, or submit anything. After that, test three different input combinations, save each one, and stop when all three run without errors. End with a brief guide that tells me which values to edit for [width], [height], [density], and any other controls.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Wire an MCP math server into your agent
They let an agent route math work to MathKernel, which planned the request and delegated computation to several theorem and numeric engines.
Set up behaviors for a small ROS2 robot
A builder used an onboard agentic OS to program a compact robot through behaviors, code tools, and ROS2 topics.
Turn a feature phone into a tiny AI controller
They loaded an AI-driven chat tool onto a Nokia 110 and used it to carry out a few simple device actions.
Search for room-temperature magnetic semiconductor candidates
A Claude Opus 5.5 agent team screened Luttinger-compensated magnets and surfaced two predicted room-temperature magnetic semiconductor candidates.
Use Ghidra tools to map a binary faster
An MCP bridge let an agent decompile code, trace relationships, and rename symbols inside Ghidra from Claude or Cursor.
Use agents to probe open mathematical questions
A group built a math environment where agents chose their own leads, ran tests, and shared findings without a central planner.