Track 1
Agent fundamentals
The orchestration loop, tool use, ReAct, memory, context engineering, and agentic RAG.
Module 1
What is an agent?
LLM as a reasoning engine, the agent loop, and when you actually need an agent.
Module 2
The orchestration loop
The core loop that powers every agent: input, reasoning, action, observation, repeat.
Anatomy of the orchestration loop
Input, reasoning, action selection, execution, observation, repeat.
Loop control: exit conditions and convergence
Max iterations, goal satisfaction, and convergence detection.
Inner loop vs outer loop
Single-turn reasoning vs multi-turn task completion.
Error handling inside the loop
Tool failures, hallucinated actions, and stuck loops.
Module 3
Tool use
How models select and invoke tools, schema design, and result injection.
Module 4
The ReAct pattern
Reasoning + Acting: the paper, the intuition, and building it from scratch.
Module 5
Memory and context engineering
Short-term, long-term, and how to manage the context window.
Conversation memory
Short-term context window management.
Summary memory and sliding window
Strategies for keeping context manageable.
Long-term memory with vector stores
Retrieval, embeddings, and when to remember vs forget.
Context window budgeting
What goes in, what gets summarized, what gets dropped.
Module 6
Agentic RAG
Agents that decide when and how to retrieve, not just static RAG pipelines.