Agents & tools
Recognise the components and boundaries that make agentic systems useful and controllable.
Your learning sequence
- 01
Agents
Explain what an AI agent is and how its loop works
- 02
Tool Calling
Explain how structured tool calls and tool results move through an application
- 03
Model Context Protocol (MCP)
Explain MCP roles, transports, and the client-server lifecycle
- 04
Skills
Explain what skills are and how the SKILL.md format packages them
- 05
ReAct (Reason + Act)
Explain the ReAct pattern and the problem it solves
- 06
Agentic AI
Explain what "agentic" means beyond a single agent definition
- 07
Loop Engineering
Explain what the agent loop is and why it needs careful design
- 08
Harness Engineering
Explain what a harness is in an agentic AI system
- 09
Human-in-the-loop AI systems
Explain what human-in-the-loop means in an AI workflow
- 10
From Prototype to Production: A Reliability Checklist for LLM Applications
A practical checklist for turning an LLM demo into a reliable production feature with measurable behavior, safe boundaries, and useful observability.
Reading is a starting point, not a proficiency score. Revisit any step whenever it helps.