Free AI courses worth your time, and the order to take them

Level 1: use AI well (no code)

• Claude Academy, from Anthropic: free courses on using Claude, prompting and working with AI day to day, at academy.claude.com.
• Prompt Engineering Interactive Tutorial, from Anthropic: hands-on exercises in writing prompts that work, on GitHub at anthropics/prompt-eng-interactive-tutorial.
• Prompt Engineering Guide, from DAIR.AI: a free reference to prompting techniques with examples, at promptingguide.ai.
• AI for Everyone, from DeepLearning.AI on Coursera: Andrew Ng's non-technical introduction to what AI can and can't do. Free to audit.

Level 2: build with AI (some Python)

• Generative AI for Beginners, from Microsoft: a lesson-by-lesson course from prompts to building apps, on GitHub at microsoft/generative-ai-for-beginners.
• Anthropic courses: notebook courses on the API, real-world prompting, evaluations and tool use, on GitHub at anthropics/courses.
• OpenAI Cookbook: working code examples for common tasks, on GitHub at openai/openai-cookbook.
• Claude cookbooks, from Anthropic: recipes for building with Claude, on GitHub at anthropics/claude-cookbooks.
• DeepLearning.AI short courses: about an hour each, many built with the companies that make the tools, at deeplearning.ai.
• Generative AI on Google Cloud: notebooks and samples for Gemini, on GitHub at GoogleCloudPlatform/generative-ai. Needs a Google Cloud account.

Level 3: agents

• AI Agents for Beginners, from Microsoft: how agents work and how to build them, on GitHub at microsoft/ai-agents-for-beginners.
• AI Agents Course, from Hugging Face: free, with a certificate if you complete it, at huggingface.co/learn.
• CrewAI and AutoGen: frameworks rather than courses, but their docs and examples are the next step once you've built a simple agent.
• Awesome LLM Apps: a large collection of working AI apps you can copy and change, on GitHub at Shubhamsaboo/awesome-llm-apps.

Level 4: understand how it works

Neural Networks: Zero to Hero, by Andrej Karpathy, is a video series that builds neural networks from scratch, up to a small GPT. It needs Python and some maths. It isn't where to start, but it's the best free way to understand what's going on underneath.

What "free" really means

Every course here is free to read or watch. Some code-along lessons call a paid API from OpenAI, Anthropic or Google. Practice usually costs little, but set a spending limit on any account you open, and keep personal or work data out of your prompts.

The bit most people skip

A finished course isn't proof. Employers see the same certificates on many CVs. What they see less often is a small, finished thing you built and can explain. So after each level, build one:

• After level 1: take a real task from your course or job, do it with AI, and write half a page on what you had to fix.
• After level 2: build a small tool that solves a problem you or a friend actually has.
• After level 3: build an agent that does one boring multi-step job from start to finish.

Test a future job before you train for it

A forecast can tell you which jobs are growing. It can't tell you whether you'd enjoy the work. Laddie, our AI coach, starts from the experience you already have and works through four steps with you:

1. 01Explore: directions your experience carries into, including work that's only now taking shape as AI changes jobs.
2. 02Try: an experiment small enough to finish this week, a small piece of the work itself.
3. 03Learn: note which part you liked and which part you avoided, and keep it as a record of what you tried.
4. 04Apply: when a direction turns into a job post, OffLadder CV shapes your CV for it. What you can't show yet goes back to Laddie as a short lesson, a 15-minute task and a mock interview.