# AI Native Course - ai-course.dev

> A free, hands-on AI course for product managers, growth leads, designers and engineers. 11 modules, 40+ copy-ready prompts, exercises, quizzes and a shareable certificate.

Last content review: August 2026. Full text of every lesson: https://ai-course.dev/llms-full.txt

Content is free to read, quote and cite with attribution to ai-course.dev.

## Course modules

### Understanding LLMs & Choosing Your AI Stack
URL: https://ai-course.dev/module/understanding-llms · ~35 min · Orientation
Before you build anything with AI, you need to understand what you're actually working with. This module covers how large language models work (in plain English), how the major models compare, and the key concepts - projects, skills, MCPs, direct connections - that will shape every decision you make going forward.

### Prompt Engineering That Actually Works
URL: https://ai-course.dev/module/prompt-engineering · ~35 min · Foundation
Most PMs use AI like a search engine. This module rewires that. You'll learn systematic prompting techniques - chain-of-thought, few-shot, role framing, output structuring - with examples grounded in real growth work.

### AI for User Research & Insights
URL: https://ai-course.dev/module/ai-for-user-research · ~40 min · Research
You already ship insight reports at your company. This module is about 10x-ing that process - synthesizing interviews at scale, auto-tagging feedback, building living insight repositories, and extracting signal from noise.

### AI-Powered Growth Workflows
URL: https://ai-course.dev/module/ai-powered-growth-workflows · ~35 min · Growth
If you're running experiments and tracking growth metrics, this module accelerates every stage of the growth loop using AI - from hypothesis generation to copy testing to experiment debriefs.

### Building AI Agents & Automations
URL: https://ai-course.dev/module/building-ai-agents · ~45 min · Engineering
You've built an insight report automation and a Contentful translation agent. This module formalizes the mental model - how to think about agents, when to use n8n vs code vs APIs, and how to design reliable multi-step workflows.

### MCPs: Build Your Own
URL: https://ai-course.dev/module/mcps-build-your-own · ~45 min · Advanced
Many teams are now building custom MCPs for their internal tools. Now it's your turn - understand them deeply, learn the anatomy, and build one from scratch. MCPs are the missing layer between AI and your internal tools.

### Proof of Concepts with AI
URL: https://ai-course.dev/module/proof-of-concepts · ~40 min · Prototyping
Build working demos before committing engineering resources. AI has collapsed the cost of PoCs dramatically - from Figma flows to website analysis to functional mini-apps that get stakeholder alignment fast.

### AI Strategy for Growth PMs
URL: https://ai-course.dev/module/ai-strategy-for-growth-pms · ~35 min · Strategy
You've learned the tactics - now build the strategic layer: where AI genuinely creates leverage vs noise, how to build your personal AI stack, and how to bring your team along as a force multiplier.

### AI Toolbox - The Right Tool for Every Job
URL: https://ai-course.dev/module/ai-toolbox · ~40 min · Tools
The AI tool landscape moves fast and the choices are overwhelming. This module maps the tools that actually matter for product, growth, design, and engineering roles - with a deep dive on Cursor as the highest-leverage AI coding tool for non-engineers who want to build real PoCs.

### AI Best Practices - Do's, Don'ts & Mental Models
URL: https://ai-course.dev/module/ai-best-practices · ~30 min · Reference
The meta-skill layer. This module teaches not just how to use AI, but how to think about using it well - the difference between a PM who gets 10% productivity gains and one who gets 10x leverage. A permanent reference you'll come back to.

### AI Ethics & Responsible Use for PMs
URL: https://ai-course.dev/module/ai-ethics · ~30 min · Ethics
This module is opinionated. Not philosophical - practical. As a PM, you make decisions about when and how AI touches your users, your team, and your company's data. This module gives you a clear framework for where to draw lines, what risks are real vs overhyped, and how to be a PM who uses AI responsibly without be…

## Glossary - plain-English AI definitions

- Large language model (LLM) (https://ai-course.dev/glossary/llm): A model trained on vast amounts of text that generates language by predicting the most likely continuation of its input.
- Token (https://ai-course.dev/glossary/token): The unit an LLM reads and writes - roughly three quarters of a word in English.
- Context window (https://ai-course.dev/glossary/context-window): The maximum amount of text a model can hold in mind at once, including your prompt, the history and any attached documents.
- Prompt engineering (https://ai-course.dev/glossary/prompt-engineering): Designing the instructions you give a model so it reliably produces the output you need.
- Context engineering (https://ai-course.dev/glossary/context-engineering): Designing everything the model can see besides your prompt: files, retrieved documents, memory, tool outputs and history.
- RAG (retrieval-augmented generation) (https://ai-course.dev/glossary/rag): A pattern where relevant documents are retrieved from your own data and inserted into the prompt before the model answers.
- MCP (Model Context Protocol) (https://ai-course.dev/glossary/mcp): An open standard that lets any AI client discover and call your tools and data sources through one interface.
- AI agent (https://ai-course.dev/glossary/ai-agent): A system where a model plans a sequence of steps and calls tools to accomplish a goal, rather than just answering once.
- Hallucination (https://ai-course.dev/glossary/hallucination): Output that is fluent and plausible but factually wrong or invented.
- Eval (https://ai-course.dev/glossary/eval): A repeatable test set that scores an AI workflow against examples of what 'good' looks like.
- LLM-as-judge (https://ai-course.dev/glossary/llm-as-judge): Using a second model call to grade the output of the first against a written rubric.
- System prompt (https://ai-course.dev/glossary/system-prompt): Standing instructions that apply to every message in a conversation or project.
- Chain-of-thought (https://ai-course.dev/glossary/chain-of-thought): Asking a model to reason step by step before answering, which improves accuracy on multi-step problems.
- Temperature (https://ai-course.dev/glossary/temperature): A setting that controls how random a model's output is - low for consistency, high for variety.
- Embedding (https://ai-course.dev/glossary/embedding): A numeric representation of text that lets software compare meaning rather than keywords.
- Fine-tuning (https://ai-course.dev/glossary/fine-tuning): Further training a model on your own examples so it internalises a format or style.
- Multimodal (https://ai-course.dev/glossary/multimodal): A model that handles more than text - images, audio, video or screenshots - in the same conversation.
- Vibe coding (https://ai-course.dev/glossary/vibe-coding): Building working software by describing what you want in natural language and iterating on what the AI produces.
- Guardrails (https://ai-course.dev/glossary/guardrails): The checks around a model that constrain what can go in and what can come out.
- EU AI Act (https://ai-course.dev/glossary/eu-ai-act): European regulation that classifies AI systems by risk and attaches obligations to each tier.

## Prompt library

Browse all 40 prompts: https://ai-course.dev/prompts
- Which AI tool should I use for this? (https://ai-course.dev/prompts/understanding-llms-which-ai-tool-should-i-use-for-this) - from Understanding LLMs & Choosing Your AI Stack
- Set up my AI Project (https://ai-course.dev/prompts/understanding-llms-set-up-my-ai-project) - from Understanding LLMs & Choosing Your AI Stack
- Should I build an MCP or use a direct connection? (https://ai-course.dev/prompts/understanding-llms-should-i-build-an-mcp-or-use-a-direct-connection) - from Understanding LLMs & Choosing Your AI Stack
- Growth brief writer (https://ai-course.dev/prompts/prompt-engineering-growth-brief-writer) - from Prompt Engineering That Actually Works
- Hypothesis generator (https://ai-course.dev/prompts/prompt-engineering-hypothesis-generator) - from Prompt Engineering That Actually Works
- Prompt improver (https://ai-course.dev/prompts/prompt-engineering-prompt-improver) - from Prompt Engineering That Actually Works
- Critique loop (https://ai-course.dev/prompts/prompt-engineering-critique-loop) - from Prompt Engineering That Actually Works
- Interrogation-first brief (https://ai-course.dev/prompts/prompt-engineering-interrogation-first-brief) - from Prompt Engineering That Actually Works
- Interview synthesizer (https://ai-course.dev/prompts/ai-for-user-research-interview-synthesizer) - from AI for User Research & Insights
- Feedback tagger (https://ai-course.dev/prompts/ai-for-user-research-feedback-tagger) - from AI for User Research & Insights
- NPS insight extractor (https://ai-course.dev/prompts/ai-for-user-research-nps-insight-extractor) - from AI for User Research & Insights
- Hypothesis generator (https://ai-course.dev/prompts/ai-powered-growth-workflows-hypothesis-generator) - from AI-Powered Growth Workflows
- Copy variant generator (https://ai-course.dev/prompts/ai-powered-growth-workflows-copy-variant-generator) - from AI-Powered Growth Workflows
- Experiment debrief (https://ai-course.dev/prompts/ai-powered-growth-workflows-experiment-debrief) - from AI-Powered Growth Workflows
- Metric anomaly investigator (https://ai-course.dev/prompts/ai-powered-growth-workflows-metric-anomaly-investigator) - from AI-Powered Growth Workflows
- Stakeholder metrics narrative (https://ai-course.dev/prompts/ai-powered-growth-workflows-stakeholder-metrics-narrative) - from AI-Powered Growth Workflows
- Agent design prompt (https://ai-course.dev/prompts/building-ai-agents-agent-design-prompt) - from Building AI Agents & Automations
- n8n workflow designer (https://ai-course.dev/prompts/building-ai-agents-n8n-workflow-designer) - from Building AI Agents & Automations
- Automation audit (https://ai-course.dev/prompts/building-ai-agents-automation-audit) - from Building AI Agents & Automations
- MCP tool designer (https://ai-course.dev/prompts/mcps-build-your-own-mcp-tool-designer) - from MCPs: Build Your Own
- MCP code scaffold (https://ai-course.dev/prompts/mcps-build-your-own-mcp-code-scaffold) - from MCPs: Build Your Own
- MCP use case brainstorm (https://ai-course.dev/prompts/mcps-build-your-own-mcp-use-case-brainstorm) - from MCPs: Build Your Own
- Website audit (https://ai-course.dev/prompts/proof-of-concepts-website-audit) - from Proof of Concepts with AI
- PoC builder brief (https://ai-course.dev/prompts/proof-of-concepts-poc-builder-brief) - from Proof of Concepts with AI
- Figma-to-insight (https://ai-course.dev/prompts/proof-of-concepts-figma-to-insight) - from Proof of Concepts with AI
- Vibe coding kickoff (https://ai-course.dev/prompts/proof-of-concepts-vibe-coding-kickoff) - from Proof of Concepts with AI
- Personal AI stack audit (https://ai-course.dev/prompts/ai-strategy-for-growth-pms-personal-ai-stack-audit) - from AI Strategy for Growth PMs
- Team AI onboarding (https://ai-course.dev/prompts/ai-strategy-for-growth-pms-team-ai-onboarding) - from AI Strategy for Growth PMs
- AI opportunity map (https://ai-course.dev/prompts/ai-strategy-for-growth-pms-ai-opportunity-map) - from AI Strategy for Growth PMs
- Build a Cursor PoC from a brief (https://ai-course.dev/prompts/ai-toolbox-build-a-cursor-poc-from-a-brief) - from AI Toolbox - The Right Tool for Every Job
- Which tool should I use for this task? (https://ai-course.dev/prompts/ai-toolbox-which-tool-should-i-use-for-this-task) - from AI Toolbox - The Right Tool for Every Job
- Audit my AI stack (https://ai-course.dev/prompts/ai-toolbox-audit-my-ai-stack) - from AI Toolbox - The Right Tool for Every Job
- Meeting transcript processor (https://ai-course.dev/prompts/ai-toolbox-meeting-transcript-processor) - from AI Toolbox - The Right Tool for Every Job
- Async thread summariser (https://ai-course.dev/prompts/ai-toolbox-async-thread-summariser) - from AI Toolbox - The Right Tool for Every Job
- Build my AI context doc (https://ai-course.dev/prompts/ai-best-practices-build-my-ai-context-doc) - from AI Best Practices - Do's, Don'ts & Mental Models
- Audit my prompt (https://ai-course.dev/prompts/ai-best-practices-audit-my-prompt) - from AI Best Practices - Do's, Don'ts & Mental Models
- Design my prompt library (https://ai-course.dev/prompts/ai-best-practices-design-my-prompt-library) - from AI Best Practices - Do's, Don'ts & Mental Models
- AI feature ethics audit (https://ai-course.dev/prompts/ai-ethics-ai-feature-ethics-audit) - from AI Ethics & Responsible Use for PMs
- Data anonymisation helper (https://ai-course.dev/prompts/ai-ethics-data-anonymisation-helper) - from AI Ethics & Responsible Use for PMs
- AI policy draft for your team (https://ai-course.dev/prompts/ai-ethics-ai-policy-draft-for-your-team) - from AI Ethics & Responsible Use for PMs

## Pages

- Home: https://ai-course.dev/
- Course map: https://ai-course.dev/course
- Prompt library: https://ai-course.dev/prompts
- Glossary: https://ai-course.dev/glossary
- FAQ: https://ai-course.dev/faq
- About: https://ai-course.dev/about
- Changelog: https://ai-course.dev/changelog

## About

Written by Arnaud Caillot - growth product manager with 15+ years building and scaling digital products. No sponsorships, no affiliate links.
Contact: https://arnaud-caillot.com

## Machine access

- Full course text: https://ai-course.dev/llms-full.txt
- MCP server (read-only: list_modules, get_module, list_prompts): https://ai-course.dev/mcp
- Sitemap: https://ai-course.dev/sitemap.xml