🤖 Using AI & AI Agents
Agent components, memory, prompting, tools, MCP, and agentic patterns
Start from Chapter 1 and work through in order, or jump to any chapter.
- 🤖→
Chapter 1 of 24
Chapter 1: What Are AI Agents?
Overview: agents that plan, use tools, and act
- 📋→
Chapter 2 of 24
Chapter 2: Types of Agents & When to Use Them
Simple reflex to multi-agent; open-ended and multi-step use cases
- 🧩→
Chapter 3 of 24
Chapter 3: Components of AI Agents
Overview: memory, prompting, tools, resources
- 📝→
Chapter 4 of 24
Chapter 4: System Prompt
Depth: what the system prompt is and how to write it
- 🎯→
Chapter 5 of 24
Chapter 5: Prompting: Zero-Shot, Few-Shot & Long Context
When to use no examples, few examples, or long context
- ⛓️→
Chapter 6 of 24
Chapter 6: Prompt Chaining
Multi-step prompts: output of one step becomes input to the next
- 💾→
Chapter 7 of 24
Chapter 7: Prompt Caching
Reuse cached prefix tokens to cut cost and latency on long prompts
- 🎯→
Chapter 8 of 24
Chapter 8: Grounding
Anchor model answers in real data: RAG, search, and citations
- 🔄→
Chapter 9 of 24
Chapter 9: Think and Act
ReAct and agentic loops in depth
- 🧠→
Chapter 10 of 24
Chapter 10: Memory in Agents
Short-term and long-term memory
- 🔧→
Chapter 11 of 24
Chapter 11: Tools & Resources
How agents use tools and read resources
- 🛡️→
Chapter 12 of 24
Chapter 12: Trustworthy Agents & Human-in-the-Loop
Safety, system message framework, threats, and human approval flows
- 📐→
Chapter 13 of 24
Chapter 13: Planning: Goals and Task Decomposition
Define goals, break into subtasks, structured output, iterative planning
- 👥→
Chapter 14 of 24
Chapter 14: Multi-Agent Patterns
When to use multiple agents; group chat, hand-off, collaboration; visibility
- 🪞→
Chapter 15 of 24
Chapter 15: Metacognition in Agents
Thinking about thinking: self-reflection, planning, corrective RAG, code as tool
- 📦→
Chapter 16 of 24
Chapter 16: Context Engineering
Managing context vs prompt engineering; types, strategies, and common failures
- 📡→
Chapter 17 of 24
Chapter 17: Introduction to MCP
Model Context Protocol: what and why
- ❓→
Chapter 18 of 24
Chapter 18: Why We Need MCP
Problems without a standard; one protocol, many apps and servers
- ⚖️→
Chapter 19 of 24
Chapter 19: MCP vs API
How MCP differs from traditional APIs: discovery, interoperability, and integration
- ⚙️→
Chapter 20 of 24
Chapter 20: MCP: Client, Server, Host, Resources & Tools
Client, server, host; exposing resources and tools
- 🚀→
Chapter 21 of 24
Chapter 21: How to Expose Your MCP Server
Build and expose tools, resources, and prompts
- 🤝→
Chapter 22 of 24
Chapter 22: Agent-to-Agent (A2A) Protocol
Agents talking to agents across systems; agent cards, executor, artifacts
- 🌐→
Chapter 23 of 24
Chapter 23: Natural Language Web (NLWeb)
Natural language interfaces for websites; MCP, embeddings, and discovery
- 🛠️→
Chapter 24 of 24
Chapter 24: Resources, Flows & Frameworks
OpenClaw, LangGraph, Cursor/Claude for coding, n8n; good agent flows