JetBrains AcademyBy the end of this course, you will be able to:
Understand the core ideas behind machine learning, neural networks, and large language models;
Work with tokens, embeddings, and context to guide model behavior;
Design effective prompts using zero-shot, few-shot, and reasoning-based techniques;
Use APIs to build applications with foundation models, including tool and function calling;
Build retrieval-augmented generation (RAG) workflows for knowledge-grounded responses;
Create simple AI agents with memory using Thought-Act-Observe loops;
Explore multi-agent systems and common orchestration patterns.
Note: This course assumes prior knowledge of core Python topics, including variables, control flow, functions, and basic data structures. Some experience with NumPy, pandas, or scikit-learn will also be useful. If you need to review these skills, we recommend taking the "Python Fundamentals with Practical Projects" course first.
Master advanced engineering concepts through ambitious projects. Each project deepens your expertise and transforms you from an experienced engineer into an exceptional one.
In this project, you'll build a customer support system made up of multiple AI agents working together. A manager agent reviews each support ticket and assigns it to the right specialist — whether it's for technical issues, billing questions, or account management. Through this hands-on project, you'll see how AI agents can cooperate, share tasks, and solve problems as a team.
Graduate
The rise of large language models is changing how we process data and develop software. LangChain provides the essential tools to bridge the gap, making it easy to incorporate LLMs into your applications. This project offers a practical, hands-on introduction to LangChain. You'll learn the core concepts and techniques for developing intelligent, LLM-driven applications by building a system that answers questions about planets.
Graduate
In this project, you'll build an interactive CLI assistant that turns a loose folder of Markdown notes into a searchable, AI-powered knowledge base. It loads your documents, indexes them in a vector store, and lets you ask natural-language questions that return answers and source citations. Beyond retrieval, it can generate brand-new notes from a topic prompt, then summarize, extract key points, improve, or translate any existing note, saving every result back to disk through function calling. By the time you're done, you'll have a self-contained terminal tool that reads, writes, and reasons over your personal notes.
Graduate
