Retrieval-Augmented Generation lets language models answer with facts pulled from your own data instead of relying solely on what they were trained on. This course builds that skill using Flowise AI, a no-code platform for assembling RAG and agent workflows, so no programming is required.
How the course progresses
- RAG fundamentals: how it works and where it beats plain generation
- RAG architecture: chunking, embeddings, vector search, and how retriever and generator components interact
- Building simple RAG systems, including a personalized tutor
- A RAG-based chat assistant for customer support, with document storage and query expansion
- Advanced techniques like tool calling, chain-of-thought prompting, and prompt chaining
- Agentic RAG systems that call external tools such as calculators and reasoning chains
- Deploying a finished RAG application with sharing enabled
Who takes this course
Past participants have come from companies including Google, OpenAI, Microsoft, Meta, JPMorgan Chase, Amazon, and Apple, alongside professionals in AI, data analytics, customer support, and research more broadly. Prior completion of prompt engineering coursework is recommended but not required.
