Figr – AI that thinks through product problems before designing
Built Figr AI because I got tired of AI builder tools market themselves as design tools and end up skipping the hard part. Every tool I tried would jump straight to screens. But that's not how product design actually works. You don't just design screens. You think through the problem first. The flows, the edge cases, the user journey, where people will get stuck. Then the design comes finally. Figr does that thinking layer first. It parses your existing product via a chrome extension or takes in screen-records, then works through the problem with you before designing. Surfaces edge cases,…
In plain words
Figr is an AI tool that helps product designers work through problems before creating screens. It analyzes existing products through a Chrome extension or screen recordings, then maps user flows, identifies edge cases, and generates specifications before moving to design. The tool focuses on the planning and thinking phase of product design rather than jumping directly to interface creation, drawing on a database of over 200,000 UX patterns and principles. It's built for product designers and teams who want to establish solid problem-solving foundations before designing.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Built Figr AI because I got tired of AI builder tools market themselves as design tools and end up skipping the hard part. Every tool I tried would jump straight to screens. But that's not how product design actually works. You don't just design screens. You think through the problem first. The flows, the edge cases, the user journey, where people will get stuck. Then the design comes finally. Figr does that thinking layer first. It parses your existing product via a chrome extension or takes in screen-records, then works through the problem with you before designing. Surfaces edge cases, maps flows, generates specs, reviews UX. The design comes after the thinking. It is able to do so because we trained it on over 200k+ real UX patterns and UX principles. Our major focus is on helping in building the right UX by understanding the product. The difference from Lovable/Bolt/V0: I think those are interface builders. They are good when you know exactly what you want to build but they don't truly help in finding the right solution to the problem. Our aim with Figr is to be more like an AI PM that happens to also design. Some difficult UX problems we've worked through with it: https://figr.design/gallery Would love feedback, especially from folks who've hit the same wall with other AI builder/design tools.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
