This is a comprehensive, intensive 6 week course that equips you to create and deploy Autonomous Agents for commercial impact. You will master Agentic AI Architectures, Frameworks and Protocols, such as the remarkable MCP. You will build 8 powerful Agent solutions that can make decisions and take actions in ways that will astonish you.
By the end of the 6 weeks, you will be able to deliver Agentic AI solutions to benefit your clients, your company and your career. Prepare for a wild ride — at times astounding, at times surreal, but always immensely satisfying.
Here is a list of useful links and resources to accompany the course.
The most common questions
My Cursor looks different to yours (new splash screen)
Can I use Gemini or free models instead of OpenAI (Yes!)
How does this course fit in with your others?
Can I take this course with no programming background?
What job can I get after taking this course?
Repo, Setup and Slides
- A link to the course itself on Udemy, along with my companion courses and how they fit together. If you’re completely new to this field, it might be worth considering the first 2 courses (AI Builder and AI Coder) as the smoothest introduction before this course.
- The Github repo at https://github.com/ed-donner/agents with the README and setup instructions
- The self-study guides for foundational information
- Slides for the course
- I have a digital twin that can answer questions on the course and curriculum
- The Proficient AI Engineer directory for graduates of my courses
And if you wish: please connect with me on LinkedIn, follow me on X, subscribe to me on YouTube, and register below! All the multi-modal forms of me 😂
Summer 2026 Upgrade to this course
The course has been upgraded with a massive update! If you’re currently on the original course, here are answers to key questions:
How do I upgrade the code?
What changed?
Why did it change?
Important – updating your code each week
I regularly push updates to the labs, including more tips, business applications and exercises. Please do pull from Github regularly to get the latest code – instructions are in the guides folder for those new to Git.
The definitive answer to the most common first question!
People from a non-Data Science background often ask me a great question: so what exactly are these “parameters” that we keep hearing about?? I’ve made this short video playlist to explain what they are, and how they give GPT its super-powers, followed by a peek inside GPT.
Contributing to the repo
Many students have contributed their own solutions and extensions to the repo. I’m incredibly grateful! I love seeing your progress and innovative ideas, and it adds value for everyone else on the course. As an added benefit, you get recognition in GitHub as a contributor to the repo.
If you’re interested in adding your work, please submit a Pull Request and I’ll merge as soon as possible. There are instructions in the guides for submitting a PR. Please make changes in the community_contributions folders only (unless you find a mistake in my code!) and Clear Outputs, as the instructions explain. Let me know if you have any problems, and massive thanks in advance.
Useful links
Here’s a link to the seminal post from Anthropic on Building Effective Agents.
AI Engineering & Coding Agents explanations & demos
Here are playlists of extra content on LLMs, Agents and Coding Agents. This is related to everything covered on all my courses. If you enjoy the videos, please like and subscribe – that’s how I know to make more!
Claude Agent SDK
As I mention in week 6, we only briefly cover Claude Agent SDK because it’s not really an Agent Framework; it’s an all-in Agent Harness – a way to programmatically drive Claude Code. But here’s an extra video to cover it:
Creating your own MCP Server
In the course we create a stdio based local MCP Server. If you’d also like to see how to create and deploy a remote MCP server over Streamable MCP, here’s a walkthrough – it’s surprisingly easy.
Frontier models – API
- GPT API from OpenAI
- Claude API from Anthropic
- Gemini API from Google
- DeepSeek API from DeepSeek AI
And here’s the Artificial Analysis leaderboard.
Here is the game I made, Outsmart, that pits models against each other in a battle of negotiation.
The New New Thing – Video Agents
If you’re interested in this emerging field, here’s a quick video on it.
Finally
Somehow you made it all the way to the end of the resources — thank you! If you’re not completely fed up with me by now, then please connect with me on LinkedIn! I’d love to stay in touch and I’m always available if you have feedback, questions or ideas.
Leave a Reply