Learn AI by building it
Learn AI, machine learning, LLMs, and AI security by building real projects. Courses and team training for developers, students, and companies, taught in English, French, and Arabic.
Courses
- AI Security for Builders: Attack and defend LLM apps: prompt injection, data leaks, and tool abuse, measured with real tests.
- Machine Learning Foundations with Python: From data to a working model: the core ideas of machine learning, built step by step in Python.
- Deep Learning in Practice: Neural networks for images and text, trained and debugged on real projects with PyTorch.
- Build LLM Apps with RAG: Connect a language model to your own documents with retrieval, and measure answer quality.
- AI Agents: Build and Evaluate: Agents with tools and multi-agent systems, built for reliability and tested like real software.
- MLOps: Ship Models to Production: Package, deploy, and monitor models on Google Cloud, from notebook to live service.
- Claude Code: Design, Build, and Ship Real Projects: No vibe coding. Learn to use Claude Code to design, build, and ship real projects faster, while you stay in charge of every change.
- LLMs for Arabic and Darija: Make language models work for Arabic and Algerian Darija: measure them, fix their weak spots, and build an app your users understand.
- Agentic Design Patterns: From the Loop to Production: Design, build, evaluate, and ship AI agents with the patterns real teams use: ReAct, planning, reflection, routing, supervisors, guardrails, memory, and evals.
- Evals for LLM Apps: Measure Before You Ship: Stop guessing whether your prompt, model, or agent got better. Build eval sets, metrics, calibrated LLM judges, and CI checks that tell you.
- AI at Work: A Practical Course for Teams and Managers: For people who don’t code. Use AI assistants well in daily work, write prompts that get results, keep company data safe, and pick the right use cases for your team.
Team training
Hands-on AI workshops, upskilling programs, and advisory for companies, schools, and universities, in English, French, or Arabic.
Frequently asked questions
Who are codewithAfaf courses for?
Developers, students, and working engineers who want practical skills in AI, machine learning, deep learning, LLMs, and AI security. Each course lists its level, from beginner to advanced.
Which languages are the courses taught in?
Courses and workshops run in English, French, and Arabic, so English, French, and Arabic speakers can learn in the language they work in.
Do you train teams and companies?
Yes. codewithAfaf runs hands-on AI workshops, upskilling programs, and advisory for companies, schools, universities, and bootcamps, online or on site, in English, French, or Arabic.
Is the course code open source?
Yes. Every course ships with open-source code on GitHub that you run, change, and keep.