AdvancedNo experience neededFree
Inside the Agent
from first tool call to autonomous agent
120 hands-on articles across 13 modules — build real AI agents inside Cursor and Claude Code, the tools professionals actually use. Tool use, RAG, MCP, context engineering, memory, the Claude Agent SDK, multi-agent orchestration, evals, security, and production deployment — every lesson read, built, and shipped in a real editor, ending in benchmarked capstones.
14
Orientation: Your Agentic Workshop15
Foundations: From Passive Prompting to Agentic Workflows16
Core Agent Concepts & Single-Agent Patterns17
Tools, APIs, Databases & RAG18
The Model Context Protocol (MCP) Deep Dive19
Context Engineering & Memory20
Claude Code & Anthropic Deep-Dive21
Building Agents in Code: The Claude Agent SDK22
Planning & Multi-Agent Orchestration23
Evaluation, Guardrails & Security24
Deployment, AgentOps & Scaling25
MCP Governance & Cross-Tool StandardsFrontier, Verticals & Capstones
You are here
Upcoming
Destination
13modules
120topics
120tasks
25–35 hrstotal
Curriculum
13 modules · 120 topicsEvery article runs concept → build → ship — the idea, a hands-on lab in Cursor or Claude Code, and a graded task you keep. Where a lesson needs a prerequisite it links to Getting Started or Beyond the Prompt instead of repeating it.
- 14.01How to Build AI Agents: What This Course Assumes FirstArticle
- 14.02How to Install Cursor AI Editor: Setup and First TourArticle
- 14.03Claude Code vs Cursor: A Beginner's Decision GuideArticle
- 14.04Cursor Agent Mode vs Ask Mode: A Risk-Dial GuideArticle
- 14.05Cursor @ Context: How to Feed the Model the Right CodeArticle
- 14.06How to Use Claude Code: Your First Autonomous LoopArticle
- 14.07Best AI Coding Agents in 2026: A Full ComparisonArticle
- 14.08Safety-First Defaults: How to Safely Use AI Coding AgentsArticle
Each topic includes a hands-on lab8 tasks
- 15.01What Is an Agentic Workflow? Prompting vs the LoopArticle
- 15.02The Augmented LLM: The Building Block of AI AgentsArticle
- 15.03What Is an AI Agent, Really? A Workflow-vs-Agent TestArticle
- 15.04How AI Agents Work: The Think-Act-Observe LoopArticle
- 15.05When Not to Use AI Agents (And What to Build Instead)Article
- 15.06AI Agent Autonomy Levels: The Full Spectrum, ExplainedArticle
- 15.07Your First AI Agent: A Real Delegated Task, Felt Not CodedArticle
Each topic includes a hands-on lab7 tasks
- 16.01Chain of Thought for AI Agents: Reasoning Picks the ToolArticle
- 16.02ReAct Agent Pattern Explained: Build the Loop YourselfArticle
- 16.03Plan-and-Execute: Why AI Agents Plan Before ActingArticle
- 16.04Agent Reflection Pattern: Why Grounded Beats IntrinsicArticle
- 16.05The Agent Self-Improvement Loop: Evaluate, Then FixArticle
- 16.06Reasoning Models & Test-Time Compute: When to SpendArticle
- 16.07What Are Agent Skills? Roles and Capabilities ExplainedArticle
- 16.08Spec-Driven Development: Specs That Steer Your AI AgentArticle
- 16.09Decision Journaling: Why Your Agent Needs a Decisions.mdArticle
Each topic includes a hands-on lab9 tasks
- 17.01How Does Tool Calling Work: The tool_use Loop ExplainedArticle
- 17.02How to Design Tools for AI Agents (Without Guessing)Article
- 17.03CodeAct vs Tool Calling: When Agents Should Write CodeArticle
- 17.04Calling External APIs from an AI Agent: A Build LogArticle
- 17.05Querying Databases From an Agent, the Read-Only WayArticle
- 17.06Structured Outputs LLM: Pydantic, Zod & ValidationArticle
- 17.07Embeddings, Vector Stores, and Why RAG WorksArticle
- 17.08How to Build a RAG Pipeline in CursorArticle
- 17.09Agentic RAG: Letting the Agent Decide When to RetrieveArticle
- 17.10Evaluating Retrieval in RAG: Precision@k ExplainedArticle
Each topic includes a hands-on lab10 tasks
- 18.01Why MCP Exists: Solving AI's N×M Integration ProblemArticle
- 18.02MCP Architecture: How Host, Client, and Server WorkArticle
- 18.03MCP Tools, Resources, and Prompts: The Control SplitArticle
- 18.04Add an MCP Server to Cursor: Config, Location & LimitsArticle
- 18.05claude mcp add: Command Syntax, Scopes & Team SetupArticle
- 18.06Best MCP Servers to Use (and How to Vet One First)Article
- 18.07Build an MCP Server with FastMCP: A Hands-On GuideArticle
- 18.08How to Build an MCP Client in Python (Step by Step)Article
- 18.09Deploy a Remote MCP Server: stdio to Streamable HTTPArticle
- 18.10MCP Authorization: OAuth 2.1 and PKCE, Hands-OnArticle
- 18.11Code Execution with MCP: Cut Token Costs Nearly 98%Article
- 18.12MCP Security: Tool Poisoning, Rug Pulls, and TrustArticle
Each topic includes a hands-on lab12 tasks
- 19.01Why Do AI Agents Forget? The Statelessness ProblemArticle
- 19.02Context Rot: Why More Context Can Mean Worse AnswersArticle
- 19.03Context Compaction: When to Use /compact and /summarizeArticle
- 19.04Notes & Tool-Result Pruning for Agent Context ManagementArticle
- 19.05Just-in-Time vs Pre-Loaded Context: A Decision FrameworkArticle
- 19.06What Is CLAUDE.md? Claude Code's Memory File, ExplainedArticle
- 19.07The CLAUDE.md Hierarchy: Scopes, @import, and RulesArticle
- 19.08Cursor Rules and AGENTS.md: Portable Agent MemoryArticle
- 19.09Claude Progress File: The Shift Log That Resumes SessionsArticle
- 19.10Database and Vector-Store Memory: When Files Aren't EnoughArticle
- 19.11MemGPT & Letta: Self-Editing Memory and Sleep-Time ComputeArticle
Each topic includes a hands-on lab11 tasks
- 20.01Claude Code Extensibility: The Full Stack, MappedArticle
- 20.02Claude Code Slash Commands: Built-In & Custom GuideArticle
- 20.03Claude Code Skills: How to Write One That TriggersArticle
- 20.04Claude Code Subagents: Isolate Context, Not DelegateArticle
- 20.05Claude Code Hooks: Deterministic Control Over AgentsArticle
- 20.06Claude Code Plugins: The Marketplace Commands That WorkArticle
- 20.07Essential Plugins, Toured
- 20.08Plugin Safety
- 20.09Building and Publishing Your Own Plugin
- 20.10Plan Mode and Multi-Context-Window Workflows
- 20.11The Initializer / Harness Pattern
- 20.12Failure Modes, Fixes, and Cursor Parallels
Each topic includes a hands-on lab12 tasks
- 21.01Agent SDK vs the Messages API
- 21.02Install and First Query
- 21.03The Agent Loop Under the Hood
- 21.04Configuring the Agent
- 21.05Choosing Your Model
- 21.06Built-in Tools
- 21.07Custom Tools and In-Process MCP
- 21.08Streaming and Sessions
- 21.09Checkpointing and Permissions
- 21.10Cost, Caching, and Reliability Engineering
- 21.11Harness Thinking and the No-Code Counterpoint
Each topic includes a hands-on lab11 tasks
- 22.01Multi-Step Planning
- 22.02The Five Workflow Patterns
- 22.03Orchestration vs Choreography
- 22.04When Multi-Agent Breaks
- 22.05Subagent Orchestration in Claude Code
- 22.06LangGraph
- 22.07CrewAI and AutoGen
- 22.08Choosing Your Orchestration Approach
Each topic includes a hands-on lab8 tasks
- 23.01Why Evals First
- 23.02Objective vs Subjective Evals
- 23.03Response, Step, and Trajectory Evaluation
- 23.04pass@k vs pass^k
- 23.05Error Analysis with Traces
- 23.06Eval Platforms and Benchmarks
- 23.07The Epistemics of Benchmarks
- 23.08Guardrails and Bounded Autonomy
- 23.09Deterministic Enforcement
- 23.10Prompt Injection and the Lethal Trifecta
- 23.11Human-in-the-Loop
- 23.12Responsible AI in Practice
Each topic includes a hands-on lab12 tasks
- 24.01From Notebook to Service
- 24.02Containerizing Agents with Docker
- 24.03CI/CD for Agents
- 24.04Observability and Tracing
- 24.05Cost and Latency Management
- 24.06State and Checkpointing at Scale
- 24.07Hosting the Agent SDK Securely
- 24.08Scaling, Enterprise Integration, and AgentOps Maturity
Each topic includes a hands-on lab8 tasks
- 25.01MCP Governance and the Registry
- 25.02AGENTS.md as a Cross-Tool Standard
Each topic includes a hands-on lab2 tasks
- 26.01Watching the Agentic Web: A2A and Agent Commerce
- 26.02Computer-Use and Browser Agents
- 26.03Multimodal Agents
- 26.04Human-Agent Collaboration
- 26.05Application Patterns Across Verticals
- 26.06Production Case Studies and the ROI Reality
- 26.07Capstone A: The Deep-Research Agent
- 26.08Capstone B: The OAuth-Secured MCP Platform
- 26.09Capstone C: The Autonomous Feature Builder
- 26.10Capstone D: Your Own Agent and Portfolio
Each topic includes a hands-on lab10 tasks