Nick Meehan

Ship Code Without Breaking Production

Ontra

Affinity

Senior SWE, AI Products at Ontra

A live walkthrough of Git and GitHub that turns foreign ground into familiar territory.

How code moves, where it lives and how to undo mistakes.

CI, staging, feature flags, rollbacks. Codebases have layers of protection. You’ll learn what catches you and when.

How your codebase is safer than you think.

You’ll walk away with specific, adoptable behaviors that make engineers actually want to work with you.

How to show up like a senior engineer.

Ship production features 2x faster by using coding agents across research, planning, implementation, testing, and review workflows

Creator of Stanford's AI Coding Course

Amazon

Stanford University

Y Combinator

Mihail Eric

Created Stanford's first AI coding class. Former YC founder and Amazon AI lead. 

Cohort 3

Cohort 4

Today many developers use AI, but few are maximally productive with it. I created Stanford's first AI software development class, and after building a YC-backed coding company and leading AI at Amazon, I've seen how top engineers integrate AI into production workflows. My techniques have been used to train 200+ Stanford engineers and industry professionals.My goal is simple: make you dramatically more productive writing software with AI than without it.In this course, you'll learn practical, end-to-end workflows for using AI in real-world development, not toy examples.We'll cover:<ul><li>Building production features with AI agents using the research → plan → implement → test workflow</li><li>Configuring an optimal AI native dev environment for your specific tech stack (IDE, code review, tool integrations, and beyond)</li><li>Setting up review and CI processes that catch AI errors, hallucinations, and slop before production</li><li>Enabling multiple agents to work together on the same codebase without conflict, accelerating software delivery and throughput</li></ul>If you're ready to write better code, ship to production faster, and stay in control of your coding agents, let's get started.

Increase developer productivity with AI-first, production-ready workflows

Configure optimal AI-first developer environments to improve your coding output

Learn how to navigate the ecosystem of cutting-edge AI developer tools 

Exercise effective strategies for prompting and building with coding agents

Reduce hallucinations, software errors, and AI slop all while shipping faster

Become a manager of coding agents so you can keep many agents productive 

Develop a deep intuition for how AI coding platforms work under-the-hood

Engineers who want to increase their productivity with AI-generated code while making it actually production grade.

Engineering managers who want to ensure their teams aren't being left behind when it comes to the new way of developing software.

Those confused about how to develop with AI the right way (how to maintain context and manage multiple agents without compromising code)

Become an AI-native builder who ships confidently with Claude Code and Codex

AI Product Leader & AI Coding Educator

MongoDB

Timescale

YouTube

Princeton University

Avthar Sewrathan

4-11 April 2026

25 July - 9 August

Most AI coding courses help you tinker. This one helps you ship.You'll build 2 real projects of your choice using the best AI coding tools on the market today: Claude Code from Anthropic and Codex from OpenAI.In the process, you'll become an AI-native builder: mastering workflows for planning, development, and testing with AI coding agents. I created this course to help you go beyond tutorials and actually ship. It's what I can't offer on YouTube: personalized support, faster progression, and accountability to ship alongside other builders.The workflows and tips you'll learn are based on hard-won experience using AI to ship production-ready software, from me and some of the best AI-native engineers in the world.And you won't build alone, with 12+ hours of office hours and Q+A across the course, a Slack community for async help, and debugging support when you hit walls.Ready to become an AI-native builder? Let's go!

Become an AI-Native Builder.  Ship real projects. Master Claude Code and Codex.

Build production apps with a repeatable AI coding workflow

Customize Claude and Codex with Plugins, Skills, and MCPs

Automate and scale with advanced agentic workflows

Navigate the evolving AI coding landscape with confidence

While sample project ideas and prompts will be provided, this course is most helpful if you have ideas for things you want to build.

Ideas for projects to build

We'll use tools like the terminal and GitHub in the course. If you're not familiar with them, no problem, just come ready to learn fast.

Willingness to learn fast

Software Engineers who want to go from tab-complete to AI-led in their planning, building, testing and review workflows.

Founders and Business Owners who want to be hands on in product development and avoid outsourcing control.

Product Managers who want to expand their impact by prototyping, testing, and shipping faster without cross-functional bottlenecks.

 Stop waiting on engineering. Build it yourself in 3 hours.  

Former Director of AI @ Microsoft, IBM

Microsoft

Coursera

UC Berkeley

NumFOCUS

Gabriela de Queiroz

Ex-Microsoft & IBM AI leader | AI Advisor for Startups

Cohort 1

Cohort 2

🚨 Last cohort was sold out. FEW SEATS LEFT!AI is changing who gets to build.PMs are shipping tools they used to request from engineering. Analysts are building dashboards they used to wait weeks for. Founders are testing ideas without hiring teams first.The gap between having an idea and shipping something real has collapsed — if you know how to direct AI correctly.In this workshop, you'll learn the workflow modern AI builders use to go from idea → working product fast.By the end of this workshop, you will have: ✅ A working AI-powered product built from your own idea ✅ My exclusive 6-Question Build Brief that you can reuse for every idea you have ✅ Your own CLAUDE.md and supporting files so Claude Code work the way you work ✅ The build-fix-adjust loop template that makes Claude Code productive instead of frustrating ✅ Custom Claude Code skills tailored for you ✅ Additional materials to support your journey after the workshop ➕ Live feedback on your idea, workflow, and product direction from an AI leader who has evaluated hundreds of AI products and startups. Cohorts are intentionally small so you can get direct support throughout the session.

Go from idea → working product in one afternoon, without writing a single line of code.

Turn any idea into a build-ready plan with the 6-Question Build Brief

Learn how to direct Claude Code like a builder

Learn the build-fix-adjust loop modern AI builders use

Learn where AI accelerates your work — and where human judgment matters

Leave with a working product built from your own idea

PMs, analysts, marketers, founders, consultants, researchers, and operators who want to move faster without waiting on engineering

Non-engineers who want to learn the workflow modern AI builders use to turn ideas into working prototypes

People who are tired of watching AI tutorials and want to actually build something real

Working with code as the raw material of software will change how you see design and what you can do with it.

Design Teacher

General Assembly

Ironhack

Edenspiekermann

BuzzFeed

Cantilever Web Design & Development

Nevan Scott

Designer/developer since before it was uncool

Making software is supposed to be fun! And this six weeks is packed with the most fun I’ve had in my 15-year teaching career.LLM-assisted coding tools can put you in the driver’s seat, working with the real materials of your craft. I’m seeing designers do things I didn’t think I’d ever get to see designers do.For as long as I can remember, product designers have been pushed away from code. Most designers settled this question for themselves long ago—code is not for me. Now is a great time to reconsider that decision. You can have a relationship with what feels like real work without spending years mastering syntactical minutiae.Working on a design with code is an act of shaping: you’re shaping something out of the raw materials yourself. And as you shape it, you can actually interact with it, get the feel of it. This means you can work on a user interface the way it really works.As designers, we enjoy making things. Working with code is a fantastic opportunity to feel connected to the thing you’re making.Read on to find out more about the course, but keep in mind that the most important things that happen in my classroom <a target="_blank" rel="noopener noreferrer nofollow" href="https://buttonschool.com/classroom/">have nothing to do with the syllabus</a>.

Learn how to use AI coding tools to build your own designs

Take the driver’s seat when working with LLM coding tools

Read code to understand the shape of what you’re making

Form a strong mental model of the architecture of what you’re building

Any amount of knowledge will work in your favor, but the course is made for designers with little-to-no coding skills.

No previous coding experience is required

The course leans into understanding—not just generating—so a desire to go beyond surface-level outputs will help you get the most out of it.

Curiosity about how things work under the hood

You should be comfortable making product decisions and thinking beyond individual screens.

Experience designing real-world products

Product designers with solid design experience but little (or zero) coding knowledge who want to build working apps of their own creation.

Product designers comfortable in tools like Figma who want to understand how web apps work and are ready to learn new tools and thinking.

Product designers who want to cut through the noise by learning how to use AI coding tools with structure, intention and control.

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

Introduction and Icebreaker

Lightning Lesson Overview

Speaker Introduction

Goal and Agenda for the Session

Understanding the Git Workflow and Key Terms

Exploring Different Branching Models

The Process of Committing Code Changes

Creating and Describing a Pull Request

Merging Code with Squash Commits

Keeping Your Branch Updated by Rebasing

Alternative to Rebasing: Merging Main into Your Branch

Pre-Commit Guardrails: Linters and Formatters

Pre-Commit Guardrails: Local Testing and Hooks

Live Demo: Failing and Bypassing Pre-Commit Hooks

GitHub Interface and Pull Request Anatomy

Live Demo: AI-Assisted Code Review and CI Checks

Testing in Staging and Preview Environments

Using Feature Flags for Safe Deployments

Continuous Deployment and Observability

Handling Production Issues: Rollbacks and Reverts

Collaborating Effectively with Your Engineering Team

Taking Ownership and Knowing When to Ask for Help

Recap and Final Takeaways

Q&A: Handling Data Changes and the Speaker's Project

Conclusion and Thank You

Product managers who drive strategy, development, and launch of products.

Broad professional audience — content relevant across many roles and functions.

Startup founders building new businesses, from MVP to scale.

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

Using AI coding assistants and tools to write, review, and ship code faster.

Using AI tools like Cursor, Replit, and Lovable to build and ship functional software without a traditional engineering background.

Ship Code Without Breaking Production

What you'll learn

Why this topic matters

You'll learn from

Nick Meehan