here's an extract from a discussion i was having in the @elyxdesign's discord with a beta tester. if you've been wondering what elyx is all about, what it does, what it doesn't do, etc. then this might help you too! elyx thrives if you treat your designs a little more like code components. even more so when they share a direct relationship with their code counterparts (e.g. button.elyx vs button.tsx). building a source of truth takes a little bit of discipline. which, let's be honest, for a very long time many of us designers had very little accountability for. we'd work in our corners, name layers however we wanted, break things into pieces based mostly on what made sense visually, often without a very good understanding of how the product was actually being built in code. that was mostly fine when design and implementation were two separate worlds. someone would eventually translate one into the other. but i think that model makes less and less sense now. if design is becoming something that teammates, agents and code all need to understand and operate on, then the structure itself starts to matter a lot more. names matter. boundaries matter. files matter. the relationship between a component in design and a component in code matters. that's a big part of why elyx can sometimes feel a bit more like an ide than a traditional design tool. it's not really trying to make the canvas less free (you can still throw whatever you want in there) but the surrounding structure is nudging you toward making things legible beyond just the canvas itself. the question for us becomes less, "how do we get you to design more before coding?" and more, "how can elyx stay useful while design and code keep feeding into each other?" that's probably the part i'm personally most excited about. not treating elyx as the place where design happens before development, but as something that can live alongside the project while it gets built.

since openai’s roadmap is pretty much entirely driven by x at this point (see ben thompson’s latest excellent piece), here’s what i would’ve done: i probably would not have created a super app, instead i would’ve created two distinct product surfaces. yes, i understand the downsides, esp heading toward an ipo, the need to grow codex users etc to prevent anthropic from running away with businesses + compute constraints. but almost every great tech company eventually became a collection of products either through acquisition or by building them. google has like 8 products with 2b+ users. fb has lots too. the main problem is that trying to turn chatgpt into a super app has created an enormous amount of complexity (which i have written about). not just technically but cognitively. there are so many modes, tools, agents, surfaces, etc that even describing the product to a normal person is getting difficult. like how do you explain dots (which is yet another surface)? chatgpt = insanely familiar consumer brand codex = work + enterprise that everyone who mattered knew about chatgpt agents could’ve become the perfect personal agents with simple, proactive, consumer first daily life things. imagine a daily feed, or proactive stuff that just works instead of having to schedule tasks. codex agents could’ve become the enterprise agent surface that at deeply integrated into work, tools, browsers, terminals, company context, etc. imagine opening up the codex app & it’s simply ready for getting shit done. each surface could still have whatever primitives it needed like voice, browser, tools, connectors. the difference is that each product would have one extremely clear job. imagine at dev day you could say 1b active users on chat & 15m codex/business customers in one slide. then launching new products becomes much easier. you can build highly opinionated interfaces for specific groups of users instead of continuously adding another abstraction into one increasingly complicated app. & you could still share ~90% of the underlying infrastructure/code. the complexity gets pushed into product boundaries rather than onto the user. i still really hate that it defaults to work when i want to chat & chat when i want to work. anyway, just my two cents from completely outside the building.

This may not age well but I don’t care. The canvas is still king for the evolution of creative ideas.

Of course I had to play with @OpenAI’s Dots. @elyxdesign works like a charm with it. I can ask for new designs from anywhere. Mobile, Slack, it all works. Elyx: Where design means more. Or as one would say, “Ubi ars designandi plus valet” (apparently).

I can say with 1000000% confidence that @elyxdesign is the next big thing for designers. I felt the same way when I switched from Photoshop to Sketch back in the day I hope that the team will add responsiveness in the same way as Framer did, so we don't need to create each breakpoint manually. But damn, I'm excited already!

Could use a few more slots 😂 It especially lacks mobile games and Pokemon Go would easily be the most played, by far!

An .elyx file is a structured, readable description of product design. And while Elyx’s main surface might be a canvas, we’re not hiding that language away behind an MCP server. You can work with the Elyx language using agents, the CLI, or directly in code view.