8:32
Agentic AI #1 — What Is an AI Agent, Really? Agents vs. Chatbots vs. Workflows
LLMwork
9:06
Agentic AI #2 — Inside the Agent Loop: ReAct and How Agents Actually Think
7:20
Agentic AI #3 — Tools & Function Calling: How Agents Touch the Real World
Agentic AI #4 — MCP Explained: The Model Context Protocol and Pluggable Tools
7:55
Agentic AI #5 — Agent Memory: Context Windows, Scratchpads, and Long-Term Recall
8:21
Agentic AI #6 — Planning & Reflection for AI Agents: Decomposition, Self-Critique & Reflexion
7:45
Agentic AI #7 — Workflows vs. Agents: The Design Patterns You Actually Need
8:00
Agentic AI #8 — Multi-Agent Systems: Supervisors, Crews, and Handoffs
8:13
Agentic AI #9 — Evaluating & Debugging Agents: Traces, Evals, and Why Agents Fail
8:10
Agentic AI #10 — Agent Frameworks Compared: LangGraph vs CrewAI vs AutoGen vs Build Your Own
8:14
Agentic AI #11 — Agents in Production: Guardrails, Cost, and Human-in-the-Loop
4:31
AI Infrastructure: The Hidden Grid Behind Every Model
4:30
Context Engineering
3:43
Embeddings: How Machines Learn the Meaning of Things
4:32
MCP Explained: USB-C for Your AI
Multi-Agent Systems: Why One AI Isn't Enough
4:33
AI Planning: How Machines Decide What To Do Next
