Guides

Complete Guide

Prompt Engineering

The full overview — what prompt engineering is, why it matters, and every technique from beginner to advanced. Start here if you're new.

Technique Guide

Chain of Thought Prompting

Ask the AI to think step-by-step before answering. CoT dramatically improves accuracy on math, logic, planning, and multi-step reasoning tasks.

Technique Guide

Few-Shot Prompting

Show the AI what you want by providing 2–5 examples. One of the most reliable ways to get consistent, structured, on-format outputs.

Technique Guide

Retrieval-Augmented Generation (RAG)

Connect AI to your own data. RAG is the most widely used pattern for building production AI that answers from real documents, not just training memory.

Architecture Guide

AI Agents

Beyond single prompts — agents reason, use tools, and iterate. Learn ReAct, tool use, multi-agent coordination, and reliable agent design.

Architecture Guide

Model Context Protocol (MCP)

The open standard for connecting AI models to external tools and data. One standard connector instead of a custom integration for every tool.

Advanced Guide

Context Engineering

The discipline of deciding what information goes into the AI's context window. Covers RAG, compression, memory management, and context positioning.

Safety Guide

Prompt Safety

Prompt injection, jailbreaking, hallucinations, and bias — the risks of deploying AI in production. How to defend and build responsibly.

Technique Guide

Image Generation Prompting

Master prompting for Midjourney, DALL-E 3, and Stable Diffusion. Style modifiers, composition control, negative prompts, and model-specific syntax.