Henry Modisett - Designing a unicorn AI startup from nothing
Dive Club đŸ€ż4 Syys 2024

Henry Modisett - Designing a unicorn AI startup from nothing

Imagine leading the design of an AI product that skyrockets to a billion+ dollar valuation in under two years


That’s the story of Perplexity and today we get to hear from their founding designer and current Head of Design, Henry Modisett. Some of the highlights from this conversation:

  • What it takes to thrive as a founding designer
  • Why Henry likes hiring designers who can code
  • The challenges of designing dynamic interfaces
  • Why Henry didn’t want to anthropomorphize the AI
  • The initial creative direction for the Perplexity brand
  • The keys to making a consumer product cognitively fast
  • Why Henry built a mini design system as his very first step
  • a lot more

SHOW NOTES

  • Ivan (CEO of Notion)’s tweet about not having a design system
  • Perplexity’s incredible brand designer named Phi
  • We talked about how booking.com is a masterclass in optimizing UI

KEY TAKEAWAYS

Starting with a design system

Before Henry had any idea what the Perplexity product would become, he built a component system in React as the first step. The goal was to give himself a toolbox to make it easy to assemble new features. Many components are obvious (ex: you know you’ll need a grid, type system, color system, buttons, etc.). We don’t have to overcomplicate design systems. They’re the thing you invest in to move fast
 not the thing you invest in once you have most of the interface figured out.

Empowerment through code

When you write code, you develop a stronger emotional attachment to the product. You’re also empowered to continually make improvements without having to go through engineers. The more removed you are from what ships, the easier it is to dish blame on someone else for an experience being janky.

“Having designers that can code is a hack
quality just happens”

Velocity is everything

Henry makes a point to prioritize velocity over exploration, debate, visual design, etc. And a big part of what makes that possible is empowering designers to make decisions. If it’s a UX question, the designer needs to make a call (”go with your gut and if you want to change it later you can”). This is also why having designers who can code is key. Nothing is cemented. You don’t need permission to iterate after something ships.

Dynamic UI systems

At the root of Perplexity are UI systems that display dynamic content based on what the user searches. That means as a designer you can’t possibly mock up all use cases. You have to think about interfaces as slightly abstracted (ex: “entity comparison” which can work for comparing dog breeds, restaurants, etc.). Part of designing a dynamic system is you have to be ok with percentage outcomes. Sometimes the formatting isn’t going to be perfect.

You’re designing the system, giving AI the tools to use, and hoping that it works most of the time.

Jaksot(185)

Hannah Hearth - Design Careers in the Age of AI

Hannah Hearth - Design Careers in the Age of AI

Today's episode is with Hannah Hearth who recently became the Head of Product Design at Vercel. We talk about all of the changes that are happening in our industry and what it all means for designers. Everything from how AI tools are changing the practice of design to how this impact the way we think about our career paths.Some highlights:Hannah’s #1 trait for great designersThe most underrated storytelling tacticDoing more with less while not burning outExamples of how AI is changing the design processHow design orgs should think about adopting AI toolsHow much coding is happening on the Vercel design teamPreserving craft and design thinking with collapsed timelinesa lot more

9 Helmi 51min

Karl Koch - Tips for New Design Engineers

Karl Koch - Tips for New Design Engineers

Get 10% off Karl's Become a Design Engineer course: https://join.dive.club/karlToday’s episode is with Karl Koch (https://x.com/_kejk?lang=en) and it’s filled with practical tips for new design engineers looking to push past what AI gives you out of the box.We go deep into:- Adopting the design engineering mindset- What the job market looks like for design engineers- The difference between frontend and design engineers- Specific language to create better interaction design- The details Karl is sweating in his role at Duck Duck Go- + a lot moreGet 10% off Karl's Become a Design Engineer course: https://join.dive.club/karl

4 Helmi 45min

Why Rive is a big deal for the future of design

Why Rive is a big deal for the future of design

This episode is a deep dive into Rive—the engine powering experiences like Spotify Wrapped, next-gen car dashboards, and so much more.After hearing Luigi and Guido Rosso’s vision for the future of interactive software, I’m convinced it will be a big deal for designers 👀

2 Helmi 43min

Best AI Coding Tools for Designers

Best AI Coding Tools for Designers

One of the biggest parts of my design practice is knowing which tool to reach for when coding with AI.There are a lot of options and they’re changing every week 😅So in this episode, I break down:1. The mental model I use to think about different types of AI coding workflows2. How that model guides which tools I actually reach for day to day3. The new AI coding product I’m completely hooked on right now- Tools listed: - Lovable (https://lovable.dev/) - Figma Make (https://www.figma.com/make/) - Dessn (https://www.dessn.ai/) - Conductor (https://www.conductor.build/) - Warp (https://www.warp.dev/) - Inflight (https://www.inflight.co)

28 Tammi 19min

Xavier Jack - How To Vibe Code in 3D

Xavier Jack - How To Vibe Code in 3D

Sometimes you open up a website and it's so good that you're left wondering... how the heck did they pull that off?In this episode the designer of the original Amie website, Xavier Jack (https://x.com/KMkota0), is going to give us a little tutorial of what it looks like to bring web experiences to life with 3D.Some highlights:- How he prototyped the viral Amie website- How he made the Amie interactive balloons from scratch- How he uses mental models to understand 3D design tools- Amie.so (http://amie.so/)- Desktop.fm (https://desktop.fm/)- Three.tools (https://three.tools/)- Shopify Winter 2026 https://shopify.com/editions/winter2026- Wiggle bones https://wiggle.three.tools/docs/manual/getting-started- Blender (3D modeling software)- Three.js (JavaScript 3D library)

26 Tammi 45min

Matt Sellers - What a top 1% design portfolio looks like

Matt Sellers - What a top 1% design portfolio looks like

Last month the head of design at Lovable, Nad Chishtie, walked us through the portfolio of one of their recent design hires, Matt Sellers.So today's episode is a behind-the-scenes of what it actually takes to create a portfolio that gets you hired at one of today's top startups.He shares some really tactical mental models that I think everyone can benefit from.Some highlights:Why Matt removed 80%+ of his workWhat made Matt's micro copy so effectiveHow Matt built his micro animations in FramerThe finer details of Matt’s portfolio and micro-interactionsHow Matt changed his portfolio strategy and why it workedWhat it takes to make your portfolio an experience rather than a cataloga lot moreNad Chishtie’s episode

21 Tammi 33min

Stephen Haney - The 2026 AI Design Field Report (tools, process, and what's working)

Stephen Haney - The 2026 AI Design Field Report (tools, process, and what's working)

There's been a heck of a debate around the future of coding and design tools lately... but what's actually happening inside of today's top teams?Where is all this headed and how does the future of our tools shape the role of a designer?Today's episode is with Stephen Haney (https://x.com/sdothaney) who is the founder of the new design tool Paper.And for the last few months he's studied how design teams actually use AI in their everyday roles... everything from tooling to prototyping to process.He walks us through some of his key findings and how that's shaping his product strategy for Paper 👇Some highlights:- The “designer playground” approach- How AI adoption looks at startups vs. big companies- Why designers at big companies aren’t PRing to production- AI usage being mandated in performance reviews for designers- The new localhost sharing problem and how teams are solving it- Why local development is winning over cloud tools for design teams- Why companies use of AI tools doesn’t match what you see on Twitter- + a lot moreBasecamp’s “Shape Up” project management philosophy (https://basecamp.com/shapeup)

19 Tammi 48min

Dessn - Is this the future of AI prototyping?

Dessn - Is this the future of AI prototyping?

Gab and Nim are the co-founders of a startup called Dessn which allows designers to prototype in the context of their production codebase (without any of the setup).So I asked them to hook it up to the Inflight repo and give me a little demo to see what’s possible.I’m pretty sold 👀

14 Tammi 34min