Lessons Map
AI engineering track
AI Engineering: LLM Basics & Prompting Learn the foundations of large language models and prompting. Understand how LLMs work, how to use them effectively, and how to get reliable, high-quality outputs.
Continue where you left off
Understand AI Engineer Last viewed 2d ago Continue lesson 0 AI Engineer Intro Goal: Understand what an AI engineer actually does before diving into how LLMs work.
1 lessons ◦ Progress: 0 / 1 lessons completed ◦ Total time: 24m
Orientation Understand AI Engineer 2 lessons fast B 24m 1 Foundations: how LLMs work Goal: Understand tokens, sampling, context, and prompting well enough to use any model API deliberately.
16 lessons 2 Models & Embeddings Goal: Know the model landscape and the vector-search substrate everything else sits on.
14 lessons 3 Retrieval & RAG Goal: Build and evaluate a production retrieval stack: chunking, hybrid search, reranking, eval.
11 lessons 4 Agents Goal: The core skill: design, build, and test tool-using agents from first principles.
10 lessons 5 Evaluation Goal: Measure and gate LLM quality: metrics, judges, golden sets, regression, eval-driven dev.
9 lessons 6 Security Goal: Secure LLM systems against injection, exfiltration, and compliance failures.
10 lessons 7 Context Engineering Goal: Treat the context as the system: layers, memory, compaction, isolation, failure modes.
14 lessons 8 Model Context Protocol Goal: Connect tools and data via MCP: servers, clients, transports, security.
6 lessons 9 Deployment Goal: Take an agent from local to deployed, monitored, and secured.
9 lessons 10 Enterprise Deployment Goal: Reference architectures, VPC/on-prem, gateways, caching, cost, CI/CD.
9 lessons 11 Adaptation & Multimodal Goal: Fine-tuning, distillation, constrained decoding, and the multimodal edges.
11 lessons 12 Forward-Deployed Craft Goal: Discovery, scoping, storytelling, and demos — the skills that multiply everything else.
4 lessons