Design × Engineering: Building a High-Taste AI Agent with Vibe Coding
Nathan Wang
18 AI Products in 18 Weeks | @Apple/Meta
Yan Liu
Principal Designer @Microsoft Ex-Spotify
Bring your idea. Ship it live in 3 weeks. Design taste meets engineering skill.
Most AI courses teach you to build something that works. This one teaches you to build something people actually want to use — and ship it live.
The Taste Gap: Your AI product works, but looks like every other ChatGPT wrapper. Users bounce.
The Skill Gap: Your designs are beautiful, but you can't actually build them. Ideas stay in Figma.
The Workflow Gap: You built a demo, but it doesn't do real work for you. It sits unused.
This course closes all three gaps in 3 weeks.
Co-taught by a Microsoft Principal product designer and an AI engineer and TPM at Apple/Meta who shipped 18 products in 18 weeks — you'll combine design taste, engineering skill, and a customized AI Agent workflow into one production-ready product.
You bring the idea. We help you build, polish, and ship it.
What you’ll learn
Bring your idea, build with design taste and engineering skill, and ship a production-ready AI product.
What makes an AI-native product?
The modern vibe coding workflow
Tools we’ll use in the course (Claude Code, Antigravity, OpenClaw, Azure etc.)
Defining user value and product scope
AI agent use cases that actually work
Visual Storytelling — use your Style DNA to create a cohesive brand experience
The next-generation AI interaction models
Style DNA, define and apply a cohesive visual identity to any product in minutes
The Taste Framework, turning rough ideas into polished UI
AI Agent Architecture — build real backend functionality with Firebase and APIs
Production Deployment — ship to a custom domain with SSL and hosting
Landing Page Design — create a conversion-optimized page that sells your product
Production Deployment — ship to a custom domain with real hosting and SSL
Go-to-Market basics — build in public, get your first users, create launch momentum
Demo Day — present your polished product to the cohort and get feedback
Who this course is for
Designers & PMs — You make beautiful mocks but can't build them. After this course, you ship real products yourself.
Founders — You have the idea and domain insight. Bring it, leave with a live product — no full team needed.
Engineers & AI Builders — Products work but feel generic. Learn design taste, build with OpenClaw, go zero to shipped.
What's included
Live sessions
Learn directly from Nathan Wang & Yan Liu in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Production starter templates
Skip weeks of boilerplate and start building your
Design system toolkit
Everything you need to make your product look premium.
Weekly live feedback sessions
Real-time design and code reviews from Nathan & Yan
Deployed product on your own domain
Not a localhost demo or Replit link.
AI prompt library
The shortcuts that took us months to develop.
Private cohort community
lifetime access to builder network
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Course syllabus
3 live sessions • 39 lessons • 3 projects
Week 1
Apr
11
Live Session 1: Design Foundations & Your First Build
🧠 AI-Native Product Thinking
💡Identifying High-Leverage AI Ideas
🎨 Designing AI Experiences
✍️ Project 1: Build Your first AI Product Prototype
🚀 Outcome
Week 2
Apr
18
Live Session 2: Full-Stack AI Engineering & Polish
🧠 AI Engineering for Product Builders
⚡ Vibe Coding Workflow
🎨 Designing for Taste & Product Quality
✍️ Project 2: Build a Functional AI Product
🚀 Outcome
Free resource
OpenClaw: When Designers Code and Engineers Have Taste
See a designer build a working AI app without code
Watch Yan Liu (Microsoft Copilot designer) go from idea to functioning AI product using vibe coding tools
See an AI agent that runs an entire daily workflow
Nathan demos his AI agent on OpenClaw: reads email, posts to social, manages calendar, ships code. All autonomous
Understand why design x engineering is the career superpower
Most AI products fail because they are built by specialists. You need to combine design taste with engineering speed
Schedule
Live sessions
2 hrs / week
2-hour weekly live build where we code together, review your progress, and unblock you. Expect short demos, guided implementation, and open Q&A so you leave each session with real features shipped—not just theory.
Sat, Apr 11
4:00 PM—6:00 PM (UTC)
Sat, Apr 18
4:00 PM—6:00 PM (UTC)
Sat, Apr 25
4:00 PM—6:00 PM (UTC)
Hands-on Project
2-4 hrs / week
Time you’ll spend building your own AI production ready app: following step-by-step tasks, wiring APIs and auth, fixing bugs, and polishing the UX so your project is ready to demo and share with real users by the end.