· advanced
Building with LLMs
What it takes to turn a working prompt into something people can rely on. Embeddings, retrieval pipelines, tools and agents, and the operational realities nobody demos.
Written in house, from the work rather than from a syllabus. Every example is one we would use ourselves, and every quiz question explains why its answer is right.
What you’ll learn
- Explain what changes between a demo and a product
- Describe how embeddings turn meaning into geometry
- Choose a chunking strategy and know its trade-offs
- Trace a RAG request end to end and locate a failure
- Tell the difference between a tool call and an agent
- Reason about cost, latency and failure before launch
Before you start
- · Generative AI Foundations, Prompt Engineering and Context Engineering
- · Some programming background helps, though no code is required