Generative AI creates text, code and images from prompts. This path goes from how large language models work to building with their APIs, retrieval-augmented generation (RAG), agents and LLMOps.
Open any step to see its lessons, tools and lab, and mark it as learning or done. Your progress is saved in this browser only.
Write clean, working Python programs
Build a command-line tool that cleans and summarises CSV data
Generative AI & RAG Engineering · AI Agents with LLMs · Build with LLM APIs: OpenAI, Claude & Gemini
Use LLMs effectively and responsibly
A reusable prompt library for real tasks
Generative AI & RAG Engineering · AI Agents with LLMs · Build with LLM APIs: OpenAI, Claude & Gemini
Integrate leading LLMs into real applications
One app that can switch between three model providers
Generative AI & RAG Engineering · AI Agents with LLMs · Build with LLM APIs: OpenAI, Claude & Gemini
Make LLMs answer accurately from your own data
Chat-with-your-docs assistant with citations
Generative AI & RAG Engineering · AI Agents with LLMs · Build with LLM APIs: OpenAI, Claude & Gemini
Build AI agents that take safe actions
Customer-support agent that looks up orders
Generative AI & RAG Engineering · AI Agents with LLMs · Build with LLM APIs: OpenAI, Claude & Gemini
Run LLM applications reliably in production
Evaluation harness that scores every release
Generative AI & RAG Engineering · AI Agents with LLMs · LLMOps & AI Observability
RAG gives a model your documents at question time, so answers stay current and can cite sources. Fine-tuning changes the model itself, which suits style and format more than facts.
Our advisors will match the path to the right SOTT course for your background.
