AI Software Development: From First Prompt to Production Code
Mihail Eric
Creator of Stanford's AI Coding Course
This course is popular
13 people enrolled last week.
Increase developer productivity with AI-first, production-ready workflows
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:
Building production features with AI agents using the research → plan → implement → test workflow
Configuring an optimal AI native dev environment for your specific tech stack (IDE, code review, tool integrations, and beyond)
Setting up review and CI processes that catch AI errors, hallucinations, and slop before production
Enabling multiple agents to work together on the same codebase without conflict, accelerating software delivery and throughput
If you're ready to write better code, ship to production faster, and stay in control of your coding agents, let's get started.
What you’ll learn
Ship production features 2x faster by using coding agents across research, planning, implementation, testing, and review workflows
Set up any AI dev environment (Cursor, Claude Code, Windsurf) with custom prompting patterns optimized for your tech stack and coding style
Choose the right AI coding tools for your use case (lessons from evaluating 100+ products in the market)
Build production features using the research → plan → implement → test → review loop that handles complex software tasks
Identify which tasks coding agents handle autonomously and which need human oversight (and set up automated checks for both)
Coordinate 3+ coding agents asynchronously on the same codebase without merge conflicts or quality issues
Build your own coding agent and MCP server from scratch to understand how Cursor and Claude Code actually work
Learn how agents like Claude Code are prompted and context engineered to handle autonomous software tasks
Learn directly from Mihail
Mihail Eric
Created Stanford's first AI coding class. Former YC founder and Amazon AI lead.
Who this course is for
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)
What's included
Live sessions
Learn directly from Mihail Eric in a real-time, interactive format.
Lifetime access to all materials and content
Go back to course content and recordings whenever you need to.
Lifetime access to a private Discord server
Join a community of peers. Stay accountable and share insights with like-minded professional developers.
4 Homework Assignments with Walkthroughs
Optional coding assignments so you can practice every concept.
10+ Hours of Live Instruction and Targeted Coaching Sessions
Open office hours for questions and personalized feedback.
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
8 live sessions • 14 lessons • 4 projects
Week 1
Start Here
Taming Coding Agents By Building Them
Jan
26
Fundamentals of Coding Agents
Jan
29
Week 1 Office Hours [Optional]
Week 2
Start Here
The AI Software Development Workflow
Feb
2
Fundamentals of Human Agent Engineering
Feb
5
Week 2 Office Hours [Optional]
Schedule
Live sessions
3 hrs / week
This covers weekly lectures and in-class exercises.
Mon, Jan 26
4:00 PM—5:30 PM (UTC)
Thu, Jan 29
4:00 PM—5:00 PM (UTC)
Mon, Feb 2
4:00 PM—5:30 PM (UTC)
Projects
2 hrs / week
Async content
3 hrs / week
This covers assigned readings, videos, and other learning materials.
Testimonials
I lead an engineering department and have been pushing our transformation to AI native development. "The Modern Software Dev" has been by far the most useful resource out there. We have been going through the syllabus one unit at a time. My entire team is shipping tons of code that is actually production quality.
Faraz Abidi
Engineering Lead, ValidThe AI tooling ecosystem is packed and overwhelming in its breadth and proliferation, and it’s genuinely hard to know where to start prioritizing your time. Mihail’s class cut through the noise and is the most effective way I’ve found to focus and maximize my limited learning time. "The Modern Software Developer" provided exactly the structure and community I needed to build an informed understanding of how AI devtools work, what offerings are best-in-class today, and how to use them effectively. I will be taking this class again!
Hannah Henderson
Senior AI Engineering Manager, HoneycombThis course made modern AI systems feel tangible and understandable. It was practical, grounded in real examples, and the guest sessions offered a fascinating look into how and why real AI products are built. I left with a much clearer mental model of how these systems work, and with habits and tools I still use every day.
Omer Freeman
Head of Customer Operations, Hud
Frequently asked questions
$1,750
USD
8 days left to enroll