Patrick Morgan
Product designer at Sublime Security, the email security company, and writer of the Unknown Arts newsletter.
Patrick Morgan did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake
Latest Newsletter
What they believe
-
Moving from static design tools to prototypes in code has helped systems-level design work, because you cannot easily grasp the many combinations of states until you have something in some form of code.
doing that kind of work in like a static environment detached from the code was always way harder than it probably needed to be because you're think trying to think through like a ton of different combinations of states that are just hard to gro until you actually get something in some form of code to be able to understand whether your your idea even makes any sense at all
youtube.comSaid 18 Aug 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.
Feed
As its own page →Hiding
30 August
19 August
18 August
From one piece Patrick Morgan - Building a custom prototyping playground 15 beliefs · youtube.com
-
Their words
in order to design the end thing that I'm aiming at, I needed to design this tool and then that tool facilitated the like the work. And I'm noticing that more and more with more designers workflow
-
Their words
your team might look very different and like your process as you sort of discover your little tensions, you just work through them. It's a product design problem to solve, you know?
-
Their words
I think for a lot of teams even just starting there or just getting your sort of centralizing your prototyping efforts so that you can start to build on your team's work like as a collective is a huge benefit
+ 12 more
-
Their words
there's so many different ways to get value from prototyping. I think when people hear prototyping, they jump immediately to highfidelity prototyping. And that's definitely not the way that I think about it or approach it
-
Their words
I think once you start to look at like what's possible in this environment, it starts to become more clear like the the b the benefits of giving yourself just enough distance. This would never go into our production like even close to our production product codebase, right?
-
Their words
many of those conventions don't serve the design process because they do things that intentionally make it hard for like the app to break, which you want in production, but you don't necessarily want in in prototype land
-
Their words
the agent can do it. It doesn't care. They're incredibly good translators. So if you just think of like production as one language of code that has its own set of constraints and semantics that are necessary for like a production app at scale
-
korrents.com
Design is no longer handed off just to an engineer; it is prepared to be reinterpreted by the engineer's agent.Their words
I'm no longer really handing off designs just to an engineer. I am pretty much preparing the design to be reinterpreted by the engineer's agent
-
Their words
even my workflow has changed so much just since the agentic coding harnesses released this ability to just directly give specific feedback on elements. That was a huge unlock
-
Their words
if you are working on something that is going to impact other people's work, that requires a higher level of review and more of a typical kind of dev workflow where we want to make sure that what you push isn't going to break stuff for other people. So my rule is you can you can break your own stuff, but you can't break other people's stuff
-
Their words
I cannot assume that the human user will be doing any of it. it's always the agent doing stuff on their behalf
-
korrents.com
Prototypes that look almost production-fidelity but are not quite right mislead people and open a communication gap.Their words
I didn't want to mislead people by creating something that was like almost production fidelity but not actually production fidelity. and then I end up with this big communication gap of like people looking at something very high fidelity but it's not quite right and so they misinterpret
-
Their words
I would be probably having it before it actually generates any UI here at all. I would just have it describe these potential approaches to me in text and I would review it that way because it would be quicker for me to gro like that seems directionally right, that seems directionally wrong
-
Their words
They're pretty lightweight. They're not super specific in terms of like exact execution or anything. They're higher level principles. But because these live in the repo here alongside the prototypes, the agent can reference them in this way to be able to use them as a tool for design
-
Their words
doing that kind of work in like a static environment detached from the code was always way harder than it probably needed to be because you're think trying to think through like a ton of different combinations of states that are just hard to gro until you actually get something in some form of code to be able to understand whether your your idea even makes any sense at all
9 August
7 June
31 May
24 May
10 May
2 March
23 February
16 February
9 February
2 February
28 December 2025
30 November 2025
23 November 2025
Nothing matches.
Beliefs
Korrents What they believe 15 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
Moving from static design tools to prototypes in code has helped systems-level design work, because you cannot easily grasp the many combinations of states until you have something in some form of code.
doing that kind of work in like a static environment detached from the code was always way harder than it probably needed to be because you're think trying to think through like a ton of different combinations of states that are just hard to gro until you actually get something in some form of code to be able to understand whether your your idea even makes any sense at all
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Design principles that are lightweight and high level, kept in the repo beside the prototypes, can be used by an agent as a tool for design.
They're pretty lightweight. They're not super specific in terms of like exact execution or anything. They're higher level principles. But because these live in the repo here alongside the prototypes, the agent can reference them in this way to be able to use them as a tool for design
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Before an agent generates any UI for an exploration, have it describe the approaches in text, which is quicker to judge as directionally right or wrong.
I would be probably having it before it actually generates any UI here at all. I would just have it describe these potential approaches to me in text and I would review it that way because it would be quicker for me to gro like that seems directionally right, that seems directionally wrong
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Show 12 more
Prototypes that look almost production-fidelity but are not quite right mislead people and open a communication gap.
I didn't want to mislead people by creating something that was like almost production fidelity but not actually production fidelity. and then I end up with this big communication gap of like people looking at something very high fidelity but it's not quite right and so they misinterpret
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
In a design tool built for agents, you cannot assume the human user will do any of it; the agent always acts on their behalf.
I cannot assume that the human user will be doing any of it. it's always the agent doing stuff on their behalf
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
In a shared prototyping environment you can break your own stuff but not other people's; anything affecting others needs a higher level of review.
if you are working on something that is going to impact other people's work, that requires a higher level of review and more of a typical kind of dev workflow where we want to make sure that what you push isn't going to break stuff for other people. So my rule is you can you can break your own stuff, but you can't break other people's stuff
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Agentic coding harnesses letting you give specific feedback directly on elements was a huge unlock for design workflows.
even my workflow has changed so much just since the agentic coding harnesses released this ability to just directly give specific feedback on elements. That was a huge unlock
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Design is no longer handed off just to an engineer; it is prepared to be reinterpreted by the engineer's agent.
I'm no longer really handing off designs just to an engineer. I am pretty much preparing the design to be reinterpreted by the engineer's agent
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Maintaining a duplicate set of prototype code is no burden for an agent; agents are incredibly good translators between code conventions.
the agent can do it. It doesn't care. They're incredibly good translators. So if you just think of like production as one language of code that has its own set of constraints and semantics that are necessary for like a production app at scale
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Many production code conventions do not serve the design process, because they make it hard for the app to break, which you want in production but not in prototype land.
many of those conventions don't serve the design process because they do things that intentionally make it hard for like the app to break, which you want in production, but you don't necessarily want in in prototype land
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Seeing what a separate prototyping environment makes possible shows the benefit of giving yourself just enough distance from production.
I think once you start to look at like what's possible in this environment, it starts to become more clear like the the b the benefits of giving yourself just enough distance. This would never go into our production like even close to our production product codebase, right?
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
There are many ways to get value from prototyping; people hear prototyping and jump to high fidelity, which is not the only way to approach it.
there's so many different ways to get value from prototyping. I think when people hear prototyping, they jump immediately to highfidelity prototyping. And that's definitely not the way that I think about it or approach it
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
For a lot of teams, just centralizing prototyping efforts so you can build on the team's work as a collective is a huge benefit.
I think for a lot of teams even just starting there or just getting your sort of centralizing your prototyping efforts so that you can start to build on your team's work like as a collective is a huge benefit
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
Building an internal prototyping environment is a product design problem to solve: your team's process may look very different, and you work through the tensions as you discover them.
your team might look very different and like your process as you sort of discover your little tensions, you just work through them. It's a product design problem to solve, you know?
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 2026
To design the end thing, a designer increasingly has to design a tool first.
in order to design the end thing that I'm aiming at, I needed to design this tool and then that tool facilitated the like the work. And I'm noticing that more and more with more designers workflow
Patrick Morgan - Building a custom prototyping playground Said 18 Aug 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 itspatmorgan.com His portfolio, writing and lab, under the line “a designer who builds”.
Personal site with Work, Lab and Writing sections; the home page says he is designing AI tools at Sublime Security, writing Unknown Arts, and building his own software with agents.
Link verified 4 Oct 2026.
Newsletter Unknown Arts Weekly essays on design, AI and creative work.
Substack newsletter, “the field guide for creative builders in the age of AI”. Recent posts: “Build a Design OS”, “Inside My AI Prototyping Environment”, “I'm Building Again”.
Recent
- Build a Design OS 30 Aug 2026 How a prototype environment became a shared operating layer for design
- Inside My AI Prototyping Environment 19 Aug 2026 A video tour of the AI-assisted prototyping tool I built at Sublime Security.
- I'm Building Again 9 Aug 2026 Why I’ve been writing less this year and what I’ve been building instead.
Show 17 more
- AI Needs a Plan 7 Jun 2026 Why the best agent work starts with a brief, not a one-shot prompt.
- Turn Your Portfolio Into a Laboratory 31 May 2026 Why your site should be a space to build, not just a space to present
- How I Rebuilt My Portfolio With Claude Code 24 May 2026 Why coding your own site is finally worth the effort and what it actually unlocks
- Designers are a Rare Breed 10 May 2026 AI is raising the floor. The ceiling is yours.
- Prototype Code Is Not Production Code (And That's Okay) 2 Mar 2026 Why the most important distinction in vibe coding is the one nobody's talking about
- Your Instructions Now Run Like Code 23 Feb 2026 Why your plain-English documentation is more valuable than ever
- Curate Your Context 16 Feb 2026 Your AI is only as good as the context you give it.
- Voice is the Missing Link 9 Feb 2026 How speaking bridges the gap between your thinking, text, and AI
- AI Runs on Text. So Should You. 2 Feb 2026 Where human thinking and AI capability naturally meet
- 2025 Year-End Letter 28 Dec 2025 What worked and didn't work this year, and what's next for 2026.
- Your Perfectionism is Lying to You 30 Nov 2025 Unpacking the counterintuitive approach that actually drives creative success
- The Myth of the Perfect Setup 23 Nov 2025 Why Gear Acquisition Syndrome makes creators busy, but not better.
- The Rhythm of Creative Progress 16 Nov 2025 What endurance training taught me about the cycles of creative growth.
- When Work Stopped Being a Place 9 Nov 2025 How we gained flexibility and lost apprenticeship.
- Solitude Is No Longer About Being Alone 2 Nov 2025 Solitude used to be a place. Now it’s a practice.
- The School of Rejection 27 Oct 2025 Don't fear rejection. Become fluent in it.
- Power Law Careers 20 Oct 2025 The collapse of tech's middle class in a winner-take-most world
Link verified 4 Oct 2026. Recent items update automatically from the channel.
x.com @itspatmorgan His X account.
Account he links from his own site; the handle matches his site, GitHub and LinkedIn name. Not read here beyond the link.
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. Dive Club’s hour on the prototyping environment he built at Sublime Security: canvases, agent-native handoff and porting production frontend.
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.