Working With AI Agents:
Five Focused Live Courses for Python Developers
Working With AI Agents: Five Focused Live Courses for Python Developers
Instructor-Led Live Courses
The agent writes the code. These courses are about everything else.
Hosted By
Core Team member at Real Python and the author of Object-Oriented Programming in Python. He teaches Real Python's Intermediate Python Deep Dive cohort and brings the same hands-on approach to each of these courses.
You use an AI agent most days. It mostly works.
But the agent was never the hard part. The hard part is everything around it:
“Why did it do that?”
“It runs. But is it right?”
“It built exactly what I asked for, and it’s still not what I wanted.”
Most developers answer those with folklore. Start a new session when it gets weird. Re-paste the context and hope. Paste the error back in and ask again.
Each rule works most of the time, and not one of them tells you why.
It doesn’t have to be that way.
What Makes These Courses Different
Instead of Learning One Tool,
You Learn What Carries Over to Every Agent
Most AI courses teach you a tool: its commands, its settings, its particular way of doing things. Then the tool changes, or you switch to another one, and you’re starting again.
These courses teach the part that doesn’t change.
Every course stands on its own, so start with the problem you have right now.
Watch this short introduction to the five courses:
The Courses
Five courses, one job each. Pick the one that matches the problem you have today.
Agentic Loops • 4 Hours • 2 Live Sessions
AI Agents for Python Developers:
Learn the Loop, Predict the Agent
Build the loop by hand in the first hour. Spend the rest of the course watching agents do things you can now see coming.
- Watch an agent start a job and say what it's going to do next, before it does it
- Answer "why did it do that?" by pointing at the reason, instead of guessing
- Recognize when an agent is stuck after two attempts instead of twenty
Checking AI-Written Python • 4 Hours • 2 Live Sessions
AI Wrote It. Now What?
Checking Python You Didn’t Write
You can produce more code than you can read. This course closes the gap.
- Read a failure and fix it without pasting the error back in and hoping
- Find the wrong answer in code that ran perfectly and raised nothing
- Tell a correction worth making yourself from an approach that needs rethinking
Building a Project With Agents • 8 Hours • 4 Live Sessions
Building Python Projects With AI Agents:
You Are the Bottleneck, Not the Agent
Eight hours, one real project, and nobody in the room types the code that ships. What you practice instead is saying what you want precisely enough to get it.
- Write a specification precise enough that an agent gets close to what you meant the first time
- Read unfamiliar agent-written code quickly and say what's wrong in words the agent can act on
- Tell code that needs a correction from a design that needs changing
Agent Teams • 8 Hours • 4 Live Sessions
AI Agent Teams for Python Developers:
From Running Agents to Running a Team
You can hand-hold one agent. You can’t hand-hold three — so you’ll learn to write down what each one’s job is instead.
- Split a job that's too big for one agent across several, each with a written job and a written boundary
- Say what a delegated agent has to report back, so a true but incomplete summary doesn't lead to a bad decision
- Leave an agent team running unattended without worrying what it might spend or quietly stop doing
Agents That Run Your Week • 4 Hours • 2 Live Sessions, Days Apart
Agents That Run Your Week:
What They Did While You Weren’t Watching
The interesting failures happen when nobody’s looking. You’ll leave three agents running for a week, then come back and read what went wrong.
- Hand a weekly chore to an agent and leave it running, without wondering whether it quietly stopped
- Write the sentence that decides what's worth telling you about, then sharpen it after a week
- Recognize the four ways unattended work goes wrong, and build against each one
Real Python Satisfaction Guarantee
Each of these courses is backed by Real Python's guarantee. You can receive a full refund within 14 days after the course ends, provided you meet the completion criteria in our refund policy.What You’ll Be Able to Do
- Answer "why did it do that?" about the agent you already use, with a reason you can defend
- Catch the code that runs, raises nothing, and is still wrong
- Say what you want precisely enough that an agent builds it, whether that's one agent or a team
- Leave agents working while you're away, and know what they did when you come back
Every Course Includes
- Live 2-hour sessions via Zoom, working through real code with the instructor
- Questions taken as they come, not held to the end
- Cohort forum with the instructor and your peers, before and after the sessions
- The code from the course, yours to keep
- A one-page reference to take back to your own work: a decoder card, a template, or a checklist, depending on the course
- Lifetime access to the recordings and materials
Who These Courses Are For
#1
Daily Agent Users who reach for Claude Code or Codex every morning and are tired of being surprised by it
#2
Faster Than You Can Read developers who are accepting code they couldn't have written and couldn't quite explain
#3
Quietly Uneasy Builders who have built something with an agent, felt something was off, and couldn't say precisely what
#4
Manual Message Buses who have hit the point where one agent can't hold the whole job and are copying context between windows by hand
#5
Weekly Checkers with a routine of looking at things that rarely change, who'd rather be told than go look
#6
The Person Who Gets Asked when an agent does something strange on their team, and would like an answer they can actually defend
Who Should Not Take These Courses?
Most of these courses assume you’re comfortable writing Python. If you’re still learning the basics, start with Real Python’s Python Basics Learning Path first. The exception is Agents That Run Your Week: if you can install a package and run a Python script, you’re ready for that one.
Meet Your Instructor
Core Team member at Real Python and acclaimed Python educator who combines years of teaching expertise and storytelling techniques to make complex programming concepts clear, engaging, and unforgettable.
Stephen Gruppetta is a seasoned Python educator and author known for his engaging narrative approach to explaining complex concepts, drawing on his PhD in physics and years as a lecturer and technical writer.
With experience ranging from corporate training to creating accessible resources like The Python Coding Book, he’s dedicated to helping learners master Python with clarity and creativity.
Why Learn With Real Python?
Real Python started as a Kickstarter project in 2012. Today, over 1 million developers, data scientists, and ML engineers read it every month.
Our content goes through what very few Python resources match:
- Expert technical review for accuracy
- Teaching specialist evaluation for learning effectiveness
- Professional editing for clarity
Our live courses bring that same review process to an interactive, instructor-led format. You get the questions, the live discussion, and a community that’s been learning Python with us since 2012.
What Learners Say About
Stephen’s Courses
“I felt like I was a really well-studied Python beginner… But I couldn’t quite get out of there to the next level. And [Stephen's course] is helping because it’s all about that deeper understanding.”
“I can look at modules, I can look at other people’s code and I understand why they’re doing what they’re doing. And it’s not just taking things for granted anymore… I can go on and start exploring more complex things without immediately getting lost.”
— Jerry Wilson, Technical Lead at AIM EMS Software
“Ever since we’ve been taking the course, I’ve really changed a lot of the way that I’m programming.”
“It’s definitely given me more confidence to go deep dive into things I just took for granted… But after this course I feel much stronger in being able to understand the fundamentals of why things work in Python that it’s given me more confidence to go deeper.”
— Matt Thacker, Sr. Solutions Engineer at Eptura
Why These Courses Work
Agents change fast. What you learn here doesn’t depend on which one you use.
Every course is live, working through real code with Stephen, with questions taken as they come. You’ll work on the situations that actually cost developers time: the agent that won’t stop, the code that runs but gives the wrong answer, the brief that gets you something you didn’t mean, the job that quietly stopped running.
You’ll leave able to work with the agents you already use, and say why they do what they do.
Five focused live courses. Pick one, or take several.
Frequently Asked Questions
Start with the problem you have right now:
- Your agent surprises you, and you want to know why: AI Agents for Python Developers
- You’re not sure the code it wrote is right: AI Wrote It. Now What?
- The results aren’t what you meant, even when they work: Building Python Projects With AI Agents
- One agent can’t hold the whole job anymore: AI Agent Teams for Python Developers
- You want agents doing routine work while you’re away: Agents That Run Your Week
Yes. Each course stands on its own and assumes nothing from the others. If you take more than one, they fit together: you’ll recognize the same ideas from different angles.
Each course page spells out exactly what you need. Most assume you’re comfortable writing Python. Agents That Run Your Week only asks that you can install a package and run a Python script. None of them assume you know how agents work internally.
Each course is either four hours (two live 2-hour sessions) or eight hours (four live 2-hour sessions), and every session runs live on Zoom.
No. The ideas apply to any agent. Claude Code and Codex are the ones we name on screen, because they’re the ones most people have open, but what you learn applies to whichever tool you’re using next year.
Each session is recorded and posted shortly afterward, so you can catch up on your own schedule. We recommend attending live when you can, since the value of a live course is asking questions in real time.
Every cohort gets a dedicated forum that runs from before the first session through to after the last. Stephen monitors the forum throughout his working day, so you can ask questions, share what you’re building, and get unstuck without waiting for the next live session.
Yes. You keep lifetime access to the session recordings, the code from the course, and the one-page reference from each course you take.
Have another question? Email us at info@realpython.com
Five focused live courses. Pick one, or take several.