I really like this idea. I’ve seen teams get stuck quibbling about details too early while using Figma. I see how this totally sidesteps that problem, similar to working with analog drawings, but with the advantage that it’s still electronic so you can stuff it into your repo and version it and also feed it into an LLM easily. I’m really curious how the LLM “sees” it. Sure, it’s characters, but it’s not language. Regardless, very cool idea. Can’t wait to give it a try.