In this hands-on course, you’ll learn how to build real AI-powered applications in modern C++ by working directly with AI APIs, HTTP/HTTPS communication, JSON, embeddings, vector representations, and Retrieval-Augmented Generation (RAG).
Instead of hiding the complexity behind pre-built AI SDKs or wrapper libraries, this course takes an internals-first approach. You’ll see exactly how requests are constructed, how JSON data is exchanged, how responses are parsed, and how AI services can be integrated into a C++ application. You’ll also learn how to connect C++ applications to OpenAI GPT models and run AI models locally using Ollama, giving you the flexibility to work with cloud-based or local AI.
What You’ll Build
Throughout the course, you’ll progressively build five complete AI-powered C++ projects, with each project introducing new concepts and extending the architecture of the previous one.
