Ed Bayes
Member of Design Staff at OpenAI, where he works on coding agents and leads design for Codex and ChatGPT Work.
Ed Bayes did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake
What they believe
-
A good framework for designing products is to design for six months out: presume model capabilities will get better and build for the world you would then be in.
One of the the key kind of frameworks I use here is like designing for 6 months out. So if you just presume that model capabilities are going to get better and you think about where we might be in six months and you kind of start to build products for that world that's kind of a good framework to to use
youtube.comSaid 9 Sept 2026This on korrents
The bold line is korrents’ wording; the quote is theirs. These one: what they wrote before what they said aloud, one per source, newest first.
Beliefs
Korrents What they believe 18 beliefs — each backed by an exact quote.
Each is a — compiled by korrents.com, not by them: the one-line wordings are korrents', the quotes are theirs.
Recent
A good framework for designing products is to design for six months out: presume model capabilities will get better and build for the world you would then be in.
One of the the key kind of frameworks I use here is like designing for 6 months out. So if you just presume that model capabilities are going to get better and you think about where we might be in six months and you kind of start to build products for that world that's kind of a good framework to to use
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
Design can add value across the whole range of the product development life cycle; it is not last-mile polish but a lot of early product thinking and exploration.
my just like general philosophy is design can add value, you know, across the whole range of the product development life cycle. It's not this kind of last mile polish. It's it's a lot of like early product thinking explorations.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
Design teams work better structured around giving designers broad scope than around features and narrow parts of the pie.
the way I like to structure teams is actually kind of less around features and you know kind of like narrow parts of the pie and trying to give designers like a broad scope
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
Show 15 more
You do not need to be able to code to be a designer, because the role of design is building a vision of the future and bringing people along.
I really don't think that you need to be able to code to be a designer like it kind it comes down to like what is the role of design and for me it's basically about kind of like building a vision of the future and then bringing people along
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
However compelling a prototype is, it will sit on your desk if you cannot convince anyone to build it, so communicating well and expressing ideas simply matter.
you can have the most compelling prototype in the world but if you can't convince anyone to build it then you know it'll just like sit on your desk so the ability to communicate really well the ability to express your ideas in very simple ways
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
With model-generated interfaces, instead of specifying the pixels you move to the skill level and define a design language within it.
instead of like specking out the pixels, you basically move to the skill level and you kind of define a uh design language, you know, within the skill.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
Scaffolding built around a model will get washed away by new model releases, so you have to stay flexible.
any kind of like scaffolding that you do like over scaffolding like some of the things that I just talked about will kind of get washed away with like new model releases. So, I think you just have to stay super flexible, right?
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
A baby-step version of eval-driven design is to sketch out 10 to 20 hero flows and run the feature or interaction through them to see where it falls apart.
the baby step version is maybe sketch out 10 20 20 kind of like hero flows you want to kind of take a crack at which you know some of these examples went through and then just basically like run it over over whatever interaction or feature you're, you know, you're trying to test out.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
The medium of designing with models is nondeterministic enough that without real prompts flowing through it, an idea can look great in a design review and be completely different when users use it.
the medium that we're working with is like so nondeterministic that without the kind of water flowing through the pipes, it's it's hard to reason about, right? Like, you know, some of these ideas like sound great on paper, but when you actually like send a bunch of prompts, as I was saying, right, with the, you know, with the visualiz, you know, building like kind of golden evals, it's like it can look great in a design review or in a prototype, but actually when users use it, it's completely different.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
Figma is still a really important tool in the toolkit, even as the scope of tools designers have access to is expanding.
there's a lot of work still happens in Figma. I think it's like a really important tool in our toolkit, but still I just think like the the scope of the tools that people have access to is expanding.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
High-trust, high-agency teams go together: you can only be high agency if you have built trust.
high trust high agency teams and they kind of can't really go without each other. So in order to be high agency and do the things that I describe which is like you know product designers like you know maybe bringing like full features to bear and like feeling empowered that they can do that. You can kind of only do that if you've built trust.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
What a design candidate builds on the weekends is as interesting as their professional experience, because this is such an exciting time to build.
when I'm kind of looking at candidates or or portfolios, I think particularly now, one thing I'm just as interested in as kind of professional experience is what are you doing on the weekends? It's such an exciting time to build.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
One of the biggest barriers to using tools like Codex is assuming it can't do something; pushing past that keeps expanding the scope of what is possible.
One of the biggest barriers of of of folks like using tools like Codex is this like limiting factor of like, oh, it can't do that. But every time, at least I've kind of like pushed myself, you know, really expands the scope of what is possible.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
The way designers still think about handoff may be slightly skeuomorphic, and there is a world, maybe within 6 to 12 months, where design is purely handed off to the engineer's agent.
the way that we're still thinking about handoff slightly skumorphic in that we have these new sets of capabilities we're exploring in code but then we almost try to retrofit it back into what we're familiar with in terms of like humanto human handoff. But in the future actually you won't even really think about the person's consumption that much and we'll purely just be handing off to our engineers agent. there is there is a world in which we get there and yeah we you know we may be there in you know 6 12 months
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
Design and product people who want to work with research should take it upon themselves to get up to speed on the latest thinking.
I think it's also kind of beholden on design and product frankly to like get up to speed on the latest thinking.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
A key challenge as agent products become more accessible is bringing safety thinking along and keeping people in control, so that, for example, a connected Gmail does not send emails without approval.
one of the key challenges now as we as we move into this this world where we're making these products way more accessible is also bringing a lot of that safety thinking and you know keeping people in control. So for example, say you connect your your Gmail, right? You know, it shouldn't just send emails for you every time you have to approve things.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
Making coding-agent interfaces more accessible expands the power of coding agents to more people, which developers got early and everyone else is now getting to know.
creating these like really accessible interfaces just really expands the access of the power of coding agents to more and more people, which developers kind of got early and now I think rest of folks are kind of uh getting to know as well.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
The final patterns for agent interfaces are not locked down at all.
So, no, I I don't think we're locked down at all um in terms of kind of the final patterns and and I think you're starting to see that now.
Ed Bayes - Designing 6 months into the future at OpenAI Said 9 Sept 2026
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
Where they publish
Site edbayes.com Personal site.
One page: a short bio of his work on coding agents at OpenAI, the studio General Purpose he founded in 2024, earlier work at Google X, and his music, with links to email, LinkedIn and X.
Link verified 4 Oct 2026.
x.com @edbayes His X account, linked from his own site.
Not read for this entry (x.com needs a login to read); listed because his own site links to it.
Link verified 4 Oct 2026.
Interviews As a guest Long-form interviews on other people’s channels, chosen and not exhaustive.
His own voice by his own participation: interviews he chose to sit for. Dive Club’s 48 minutes on designing six months ahead at OpenAI: prototyping on a branch of the real product, eval-driven design, and what he looks for in designers.
Link verified 4 Oct 2026.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.