Build with AI: Mindset, Habits & Tools for the Next 20 Years

Yuzheng Sun, PhD

Founder | Meta/Amazon/Statsig/Tencent

Yan Wang, PhD

Applied Scientist | yage.ai

This course is popular

10 people enrolled last week.

Learn AI for the Next 20 Years, Not the Next 20 Days

Is this you?

  • Chatting endlessly with an “AI intern” instead of designing the context with clear principles.

  • Blaming “hallucinations” when the real issue is poor orchestration.

  • Trying to run an entire project from a single, overloaded chat window.

  • Treating AI like witchcraft and prompt spells instead of engineering.

AI gets better every day. But when it’s time to ship something serious, you don’t yet have a reliable way to make AI show up for you.

The problem isn’t AI. It’s how you’re using it.
This course exists for that exact gap.

AI is a new computiung paradigm. To use it well, you have to:

  • Unlearn old patterns

  • Install new mindsets and habits

  • Build a meta-learning system that can carry your career for the next 20 years

That's hard, and we take it seriously.


This course is designed to teach you how to fish. On top of lessons and projects, we built two unique tools:

  1. A build platform that consolidates key APIs and lets you deploy your projects with one command—so you can build fast, not fight boilerplate.

  2. A lifetime community where you can share projects, ask questions, and get unstuck long after the course ends.

The end of our course is the beginning of your learning, and we will be with you.

What you’ll learn

We show you what's possible with AI, then take you there.

  • Build a Q&A bot over your own documents (e.g., Confluence, internal wikis) using methods beyond RAG

  • Create automated workflows, like generating weekly summary reports from Jira tickets or processing inbound emails

  • Evaluate, debug, and systematically improve the output of LLMs in a systematic way

  • Understand the core mechanics of LLMs (e.g., context windows, attention) to confidently assess new models and tools

  • Develop a first-principles approach to prompt engineering, moving beyond simple templates to gain deeper understanding

  • Identify and design systems to mitigate inherent AI limitations like hallucination and reasoning failures

  • Identify and scope high-value AI opportunities within your own business workflow to maximize impact

  • Lead an AI project from an idea to a working prototype, ready for stakeholder review and feedback

  • Clearly articulate the capabilities, costs, and limitations of a proposed GenAI solution to stakeholders

Learn directly from Yuzheng & Yan

Yuzheng Sun, PhD

Yuzheng Sun, PhD

Prev. Evangelist @ Statsig (Acq. by OpenAI), AI Director @ Tencent; Meta/Amazon

Founder of Superlinear Academy. Prev. Statsig, Tencent, Meta, Amazon
Statsig
Meta
Amazon
Boston Consulting Group (BCG)
Tencent Games
Yan Wang, PhD

Yan Wang, PhD

Applied Scientist @ Samsara | Olympic Torchbearer | Ex Pinterest/Microsoft | Ex Tech blogger with 100k+ subscribers

Who this course is for

  • Software Engineers & Developers
    Ready to build reliable, scalable AI systems integrated into production workflows.

  • Technical Product Managers & Strategists
    Seeking the hands-on knowledge to scope, architect, and guide AI initiatives with confidence.

  • Data Professionals & Automation Experts
    Who want to transform proof-of-concept scripts into durable applications that multiply productivity.

What's included

Live sessions

Learn directly from Yuzheng Sun, PhD & Yan Wang, PhD in a real-time, interactive format.

4 Hours of Live, Framework-Focused Sessions

Your learning is anchored by live sessions designed to give you a durable mental framework. We distill the most critical information on how AI works, teach you how to learn effectively, and provide concrete principles to guide you from your first line of code to a functional application.

Hands-On Projects & Live Office Hours

Solidify your knowledge through hands-on projects relevant to your daily work. In our office hours, we provide personalized guidance to unblock you, using cutting-edge tools like Cursor and Claude Code to build solutions live and demonstrate advanced problem-solving.

Extensive Library of Original Reference Materials

Your learning is supported by a 200+ page library of original materials, continuously updated to stay current. This detailed guide is designed to give you concrete answers and guidance when you encounter specific problems weeks or months after the course.

Lifetime Access to a Private AI Builders Network

Your enrollment includes lifetime access to our private network of over 5,000 professional AI builders. Share technical solutions, discuss new research, and advance your career alongside other serious practitioners in a dedicated Q&A community.

Certificate of completion

Share your new skills with your employer or on LinkedIn.

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 • 89 lessons • 5 projects

Week 1

Jan 5—Jan 11

    Jan

    11

    Live Sessions - Week 1

    Sun 1/1112:00 AM—2:00 AM (UTC)

    Automate Your Work with GenAI

    4 items

    GenAI Internals and Best Practices

    8 items

    Lightweight Projects: Bridging GUIs and APIs

    7 items

Week 2

Jan 12—Jan 18

    Jan

    18

    [Optional] Office Hour

    Sun 1/1812:00 AM—1:30 AM (UTC)
    Optional

    Jan

    19

    Live Session - Week 2

    Mon 1/1912:00 AM—2:00 AM (UTC)

    Effective Management of GenAI

    10 items

    Become Future Proof

    7 items

Free lesson

The MCP Myth: Do You Really Need a Unified Agentic Protocol? cover image

The MCP Myth: Do You Really Need a Unified Agentic Protocol?

Why was MCP created in the first place?

Understand the hidden business and technical motivations behind the push for a unified protocol in the LLM ecosystem.

How can you strategically leverage MCP?

Gain practical insights into making informed choices about MCP adoption based on real-world trade-offs.

When should you actually avoid MCP?

Discover scenarios where adopting MCP could slow you down rather than accelerate your development.

Schedule

Live sessions

3 hrs / week

    • Sun, Jan 11

      12:00 AM—2:00 AM (UTC)

    • Sun, Jan 18

      12:00 AM—1:30 AM (UTC)

    • Mon, Jan 19

      12:00 AM—2:00 AM (UTC)

Projects

10 hrs / week

Async content

20 hrs / week

Frequently asked questions

Save 25% until Monday

$1,999

USD

·
Jan 5Jan 19
Enroll