Radar / AI media tools / Confetti
Confetti: build hardware projects using plain-English prompts
A platform where makers describe a hardware project in plain English and AI agents handle CAD generation and editing, compatible off-the-shelf part sourcing with wiring and firmware, and manufacturing quotes and ordering, with community remixing of builds.
Why it matters
It treats hardware like vibe coding: the CAD, electronics and ordering steps that used to demand weeks of learning sit behind one conversation, and real builds — a portable mechanical analyzer, a custom keyboard — are the proof points.
What you could build with it
A teacher running a makerspace could set a class project on this platform: students describe a device, iterate the generated CAD and parts list, and only order after a tutor checks component compatibility, turning a semester hardware project into a week-long exercise.
Does it hold up?
Too early to judge: launched on Product Hunt on October 27 with founder-described example builds; no independent build logs, pricing, or delivery reports from buyers exist yet.
Built with Confetti
- Confetti: build hardware projects using plain-English promptsarticle · Launch post from two UPenn CS dropouts describing CAD, electronics sourcing, manufacturing ordering and community remixing, with example builds from early users.
Learn more
First spotted on article: source.
More AI media tools
Video Shotcraft: AI video skill for Claude Code & Codex that directs cinematic product promos in RemotionA skill package for Claude Code and Codex that turns a product brief into a finished promo video: the agent captures…media · JEV 0.71Lemo-Opuscar: 59 code-directed film styles for Claude CodeA toolbox of 59 film styles, each a style prompt plus a demo film made entirely in code by Claude Opus 5.5 with no…media · JEV 0.71SolidCraft: open-source parametric CAD in Rust that agents can drive over MCPSolidCraft is an open-source parametric 3D CAD application written in pure Rust (desktop, browser via WebAssembly…media · JEV 0.67Google Genie 4: real-time world model with native audio and live steeringGoogle DeepMind announced Genie 4 on 27 Oct 2026: a world model that generates photorealistic, interactive 3D worlds…media · JEV 0.62MOSS-Image-SFT: OpenMOSS 5B image model trending on HFOpenMOSS-Team (Fudan) 5B text-to-image SFT checkpoint newly trending on Hugging Face (#5 today, Oct 21): the…media · JEV 0.57Canva Craft: Canva's first in-house image model plans the design before drawing itCanva launched Craft, its first in-house text-to-image model. It plans a composition from the prompt - layout, scale…media · JEV 0.51
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.