David Gaynor and Patrick Coleman

Build an app with ChatGPT

Andela

Replit

PeopleGrove

David Gaynor

Engineer and exited founder, ex Andela and Twitter

Patrick Coleman

Former first business hire and early leader at Replit and PeopleGrove

Discover ways to use AI tools from ideation to coding to content

How we built our language learning startup Yaya

A hands-on demo of using the ChatGPT API to build an app

Working with the ChatGPT API

Talk to users early, iterate quickly, and don't overbuild

Mistakes to avoid

Build robust LLM-powered apps, chatbots, and agents. Learn by writing real code, one line at a time.

CEO @ Actualize

Jay Wengrow

Software Engineer and Educator, Author of A Common-Sense Guide to AI Engineering

Cohort 1

Cohort 2

Do you have a grasp of basic LLM principles but struggle to put it all into code? Tired of scattered documentation, outdated tutorials, and frameworks that impress in demos but collapse in production?You’re not alone. Building with large language models doesn’t have to be confusing - it can be clear, structured, and deeply rewarding.In this course, you’ll build real LLM-powered apps, one line of code at a time. You'll see how an app is built from scratch in real time, and follow along. Along the way, you'll discover not only how to implement these systems, but the why behind each line of code.From chatbots to agents and RAG to evals, you’ll learn the core concepts of building atop LLMs. More importantly, you’ll get how LLMs “think” - allowing you to guide them to do what you want despite their nondeterministic nature. Additionally, you’ll be able to balance quality, latency, and cost, making big-picture decisions about AI-powered app architecture.AI engineering isn’t just another branch of software development - it’s a different mindset altogether.

Gain hands-on AI Engineering proficiency by writing real code

Gain real-world intuition for working with LLMs

Reliably guide LLMs instead of getting unpredictable results.

Build retrieval-augmented assistants that can access proprietary knowledge

Use evals to systematically optimize your LLM app’s performance over time

Assemble agents that act upon the real world

This course is designed for current software engineers who will use Python  to build LLM-powered apps. We won't teach basic coding here.

Software Engineering

We'll be using Python, but we'll keep it simple in case you're more familiar with other coding languages.

Note about Python

If you want an inside look at what's involved with building AI apps but don't plan on coding yourself, you'll still follow what's going on.

Exception: Product Managers

Software engineers who want to build LLM-powered chatbots and agents, or break into AI engineering more generally

Data Scientists/Engineers who want to build their own LLM-powered apps

Product Managers who want to understand AI engineering from the coding perspective

Publish an App to OpenAI's Appstore, for 900 million users.

Founder, Level 250 | 3x VP, API Products

Verisk

Moodys

Oracle

SmartBear

Precisely

Emmanuel Paraskakis

3x VP Product (Apiary, Swagger, Oracle) | 1.3M APIs | Agent-ready APIs & MCP

1 month of Fractal Pro included.Do you ever wish you were building apps when the iPhone App Store got started? ChatGPT has 900 million weekly users. They can install apps. Yours could be one of them.The opportunity is real but the path is unclear. The SDK docs have errors. The submission form is hostile. The review process is opaque. Hidden requirements that aren't in any documentation. Most people give up before they ship.In this workshop, you'll build a ChatGPT app from scratch using Fractal, a no-code builder for MCP apps. You'll learn the Know / Do / Show framework for what makes a good app, set up developer mode to test locally, and walk through the full submission process including every undocumented gotcha.You'll leave with a working ChatGPT app you tested in developer mode, a month of Fractal Pro to keep building, and a submission checklist covering every rejection reason.There are about 600 apps in the directory today. This is the early iPhone App Store. The builders who show up now will have a head start when the ecosystem takes off.Walk in with an idea. Walk out with an app ready for 900 million users.

Product Managers who want to ship a ChatGPT app for their product and navigate the submission process.

Founders and Makers who want to get into the ChatGPT directory early - about 390 apps today, like the iPhone Appstore in 2008, but for AI.

Engineers who want to prototype their first ChatGPT app with no-code tools and skip the undocumented gotchas.

Go from staring at a blank folder to a Claude Code AI system that you actually use in your life or business, in 6 weeks.

AI Systems Builder at GenAI Unpugged

Dheeraj Sharma

Founder, GenAI Unplugged. Ships AI systems. Claude Code, n8n, agentic workflows.

Founding Batch

You watched the YouTube tutorial. You installed Claude Code. You opened a terminal and stared at a blank folder. The bar for what anyone can build alone is rising fast. The gap between people who use AI tools and people who build AI systems widens every month. Most Claude Code attempts die in 20 minutes. Not because the tool is hard, but because nobody showed you what is possible before asking you to build.Tutorials &amp; self-paced courses don't get you there. You need an instructor watching as you build, and other builders alongside you so you don't disappear after Week 2.In 6 weeks, you build a Claude Code system that runs your business: ✅ turns your inputs into your outputs in your voice; ✅ connects to your real tools (Gmail, Notion, Google Drive, Calendar, Obsidian, Tavily) through 3-5 MCP servers; ✅ automates multi-agent pipelines through a live Hot Seat Build; ✅ reaches you on your phone; runs on a schedule without you. Taught live by Dheeraj Sharma, Founder of GenAI Unplugged, 9 AI products shipped, 75+ articles on building AI systems for solopreneurs.Session 1 Guarantee: Leave with clarity and confidence that this cohort is right for you. Else full refund. No questions.

Stop staring at the blank folder. Build a Claude Code AI system that ships.

01. Pick the right problem to automate with Claude Code 

02. Install Claude Code and ship your first working system

03. Build a knowledge layer that makes outputs sound like you

04. Wire your system into your real tools with MCP

05. Build multi-agent pipelines through a live Hot Seat Build

06. Run your first scheduled agent and ship your capstone

You will be typing in a terminal during live sessions. A real keyboard and full OS are required.

A laptop for each live session (Mac, Windows, or Linux. No tablet-only setups)

Claude Code runs on your Claude account. Free tier will hit limits during the live builds. Pro is the minimum.

An active Claude Pro subscription ($20/month) or Claude Max

<pre><code class="language-markdown">AI-Curious Professional who uses ChatGPT daily but wants to BUILD AI systems that run their work, not just chat with an assistant.</code></pre>

<pre><code class="language-markdown">Content creator or newsletter writer who tried Claude Code once, hit the blank folder, and gave up before shipping anything.
</code></pre>

<pre><code class="language-markdown">Solopreneur or small business owner drowning in research, drafts, and client summaries who wants AI system to handle the repeat work.</code></pre>

Build and launch your app fast—no code needed. A hands-on 3-week course to turn your idea or design into a published MVP.

IT Professional & NoCode Evangelist

Diana Lugova

Founder and NoCode app builder. Degree in Applied Math. Passion for innovation. 

Are you a non-technical founder, product manager, or creative professional with a groundbreaking idea but no coding skills? Or UI/UX designer with great skills to create design and prototype in Figma – but then stop at not being able to deliver Beta?This hands-on, intense 3-week live cohort course is designed to help you:Build web applications without writing a single line of code using Lovable.Integrate advanced tools like OpenAI, Supabase, and Stripe and several others to create a full stuck MVP.Launch a functional Beta by the end of the course and start testing it with real users.&nbsp;

Transform into NoCode developer with Lovable

Learn how to build and launch a functional web app MVP in 3 weeks using Lovable

Comfortable navigating web browsers and online platforms.
Ability to create accounts and use web-based tools.

Basic Computer Skills

Specific problem you want to solve.
OR a rough concept for an app/product you want to build.
Willingness to refine and pivot your idea.

Application Idea

Basic understanding of user experience principles would be helpful.
Some familiarity with design thinking approaches.

UI/UX Design Skills would be helpful but not required

UI/UX and Figma Designers. Add NoCode development to your toolbox and expand your service offerings. Expand your skill set.

Non-tech Founders with great SaaS ideas. Launch your MVP without hiring expensive developers.

Graphic Designers and Freelancers. Raise your rates and offer app development services to your clients.

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Engineers and engineering leaders who build, deploy, and scale software systems.

Startup founders building new businesses, from MVP to scale.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Build an app with ChatGPT

What you'll learn

Why this topic matters

You'll learn from

David Gaynor

Patrick Coleman