COURSE SCHEDULE
Daily Breakdown
Day 1: LLM Foundations
Prompting, context and control: how a model reads a prompt, how to get output your code can parse, how sampling and memory work, and how an instruction hidden in the data takes over.
Day 2: Retrieval-Augmented Generation
Retrieval, embeddings and evaluation: answering from your own documents with sources, and measuring whether retrieval and generation actually work.
Day 3: Tools, Loops and Agent Architectures
From chatbot to agent: tools with contracts, MCP, the agent loop, ReAct, CodeAct, plan-and-execute and Reflexion, and the guardrails an agent needs before it acts.
Day 4: Multi-Agent Systems and Human-in-the-Loop
When one agent isn't enough: agentic retrieval, orchestration patterns, shared state between agents, approval gates and escalation, and how multi-agent systems fail.
Day 5: Testing, Patterns and Production
How to know an agent works and keep it working: layered testing, LLM judges, observability, advanced patterns, research agents and real-world architectures.