Go from vague requests that produce mediocre outputs to precise, reproducible prompts that work every time. The skill that underpins everything else in AI.
Prompt engineering is the practice of writing clear, structured messages that reliably produce the AI outputs you want. It covers techniques like chain-of-thought (asking the model to reason step by step), few-shot examples (showing the model what good looks like), and output format constraints. Without prompt engineering fundamentals, even powerful AI models produce inconsistent, hard-to-use results.
Prompt engineering is broader than using any single product. The techniques — zero-shot, few-shot, chain-of-thought, structured output — apply across Claude, GPT, Gemini, and any other LLM. This pathway teaches model-agnostic fundamentals, not product-specific tips that become obsolete when the product updates.
11 articles, approximately 5 hours total. Many practitioners revisit individual articles when working on specific prompt engineering problems rather than reading all 11 in sequence.
Understand what AI actually is — tokens, transformers, agents, and the landscape. Start here if you're new.
11 articles · ~4h →Go from zero to productive with Claude Code — the terminal AI coding agent that ships real projects.
15 articles · ~7h →Understand and build the loops, harnesses, and protocols that make AI agents reliable and autonomous.
16 articles · ~6h →Mollick: Prompting Tricks Are Over — Write Specs
Wharton Prompting Science Reports 1–4 on CoT, personas, tips, and management.
What Is a System Prompt?
The hidden instructions that shape every AI response — explained.
Zero-Shot vs Few-Shot vs Chain-of-Thought Prompting
Three prompting paradigms and when to use each.
Temperature, Top-P, and Top-K in LLMs
The sampling parameters that control creativity and determinism.
Context Engineering: Why Clean Prompts Matter
The full discipline of assembling everything the model sees — from RAG to tool schemas to history.
ReAct Prompting: Reasoning + Acting for AI Agents
The Thought/Action/Observation loop that powers most modern AI agents.
Structured Output & JSON Mode Prompting
Get reliable JSON from LLMs — schemas, validation, and retry patterns.
Structured Output with tool_use and JSON Schemas
Why tool_use guarantees schema compliance when JSON-in-prompt doesn't — nullable fields, validation-retry loops, and enum design.
How to Evaluate Prompt Quality
Build an eval set, run A/B tests, and measure what actually matters.
Top AI Prompts for Coding
20 structured templates that actually produce useful code.
Top AI Prompts for Productivity
20 structured templates for getting more done with AI.
Top AI Prompts for Research
20 structured templates for AI-assisted research work.
Master Prompt Engineering with Claude
Claude-specific patterns and techniques for better outputs.
Practical AI adoption for your specific function — marketing, engineering, HR, finance, and more.
10 articles · ~4h →
