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.

Repo, Setup and Slides

• A link to the course itself on Udemy, along with my companion courses and how they fit together – this includes my brand new course on Building Agents and Voice Agents with n8n
• 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
• Common FAQ for my courses
• Other links: my Live Events and the Proficient AI Engineer program

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 😂

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.

Another fun example project

Here’s a video extra on a project to have LLMs compete that shows how easy it is to use different Frontier APIs, and the benefits of writing your own lightweight LLM abstraction.

Here’s a review of OpenAI’s latest chat model, GPT-4.5:

Frontier models – API

1. GPT API from OpenAI
2. Claude API from Anthropic
3. Gemini API from Google
4. DeepSeek API from DeepSeek AI

And here’s the Vellum leaderboards including costs and context windows.

Here is the game I made, Outsmart, that pits models against each other in a battle of negotiation.

The Extra Extra Project for Fun

I mentioned my experiment to train an LLM on my 240,000 text message history. My write-up of the journey is here, and the subsequent blog posts take you through the adventure of replicating this yourself!

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.