Practical AI Logo
Practical AI
A community for real world AI.
Practical AI Thessaloniki is a community dedicated to showing how AI addresses real-life needs with practical solutions. Each session tells a story, beginning with a real-world problem, planning a solution, and demonstrating AI tools, many from the open-source community, that are tested to meet the need.

Attendees experience AI beyond theory, seeing it applied in practical scenarios. We explore these tools hands-on in collaborative sessions, making AI accessible and relevant.

Our mini-course catalogue

All our meetup builds are broken into free, small, guided courses. Each one includes a clear goal, setup instructions, steps, and a runnable example. Start anywhere, learn at your speed.

Our meetups

We run meetups every quarter to bring builders together and ship practical demos. Come to watch an end to end build, ask questions, and meet people doing the work.

Latest courses
Browse all courses
Setting Up Your First MCP Server
2h 30min
Beginner
In this mini course, you'll set up a complete Python development environment for building MCP (Model Context Protocol) servers and create your first working server with tools and prompts. You'll install all necessary dependencies, configure an MCP client, and test your server interactively.
Building Reliable AI Evaluation Pipelines
3h 15min
Advanced
Learn how to design and run evaluation pipelines for large language models. This course covers the fundamentals of LLM evals, from writing test cases to automating scoring with model-based judges.
Build a RAG Pipeline from Scratch
2h 00min
Beginner
Retrieval-Augmented Generation (RAG) lets you ground LLM responses in your own data. In this course you'll chunk documents, embed them into a vector store, and wire up a retrieval step that feeds relevant context into your prompts.
Prompt Engineering for Reliable Outputs
1h 45min
Beginner
Prompts are code. This course teaches you how to write, version, and test prompts that produce consistent results across model updates. You'll cover chain-of-thought, few-shot examples, output formatting, and common failure modes.