Beginner · Free
Getting Started
From zero to live AI app. No experience needed.
10 modules
AI Landscape
Terminal
Dev Setup
Git
Python
Web Basics
Backend
AI Tools
Deploy
Live Project
101 topics
A Place toLEARNAI Skills.
From your first prompt to production-grade agents — clearly written, well-sourced guides for beginners and builders alike.
- Beginner Friendly
- Production Focused
- Expert Crafted
- Practical Examples
Prompt Engineering
Agentic AI
Tools
RAG
LLMs
Evals
Deploy
Learning paths
Structured paths through AI — pick your level.
Advanced · Free
Beyond the Prompt
From first prompt to production-grade prompt system.
3 modules
Foundations
Builder
Production & Frontier
31 topics
Flagship · Free
Inside the Agent
From your first tool call to autonomous agents — built where the pros build.
13 modules
Orientation
Foundations
Patterns
Tools & RAG
MCP
Memory
Claude Code
Agent SDK
Multi-Agent
Evals & Sec
Deploy
Standards
Capstones
120 topics
Everything AI, in one place
Nine topic areas covering everything from AI basics to advanced agentic systems.
Fresh from the library
Recent articles across AI topics — updated regularly.
agentic aiintermediate
What Are Agent Skills? Roles and Capabilities Explained
What are agent skills? Named, triggerable behaviors with clear steps and gotchas. See how skills, roles, and capabilities differ before Module 20.
8 min read·Hasnat Tariq
Read article →
agentic aiadvanced
CodeAct vs Tool Calling: When Agents Should Write Code
CodeAct lets agents write and run code instead of JSON tool calls, cutting round-trips but adding sandbox risk. Here's how to choose.
10 min read·Hasnat Tariq
Read article →
agentic aiintermediate
Decision Journaling: Why Your Agent Needs a Decisions.md
A decision log records what you chose, why, and what you rejected, so neither you nor your agent re-argues a settled call. Here's how to build one.
7 min read·Hasnat Tariq
Read article →
agentic aiintermediate
How Does Tool Calling Work: The tool_use Loop Explained
How does tool calling work? The model stops mid-turn, emits a tool_use block naming a tool and its input, and your code runs it and returns a tool_result.
9 min read·Hasnat Tariq
Read article →
agentic aiintermediate
Spec-Driven Development: Specs That Steer Your AI Agent
Spec-driven development turns a vague feature request into a versioned spec an AI coding agent builds from, catching ambiguity before code does.
10 min read·Hasnat Tariq
Read article →
agentic aiintermediate
The Agent Self-Improvement Loop: Evaluate, Then Fix
The agent self-improvement loop is plan, execute, evaluate against one number, then refine. Learn why skipping the metric turns improve into just change.
8 min read·Hasnat Tariq
Read article →