Applied AI

25 skills in 8 steps, from “Work with a coding agent” to “Assemble, observe and secure a sovereign AI stack”.

Start · Install Claude Code and drive a session on a project All skills

25 skills to acquire in this domain
8 steps in the order you learn them
0/25 acquired from your progress, in this browser
4 prerequisite domains to know before starting here

Your path

The domain's steps

In the order you learn them: each step builds on the previous one. Your status is computed in your browser, from what you have read and passed (quizzes, labs).

1

Work with a coding agent

3 skills
See the 3 skills
- Install Claude Code and drive a session on a project 5 lessons · ~3 h 25 · then its quiz
- Scope a task given to Claude Code and check its result with a plan, a diff and tests 4 lessons · ~2 h 45 · then its quiz
- Take back control of a drifting Claude Code session and troubleshoot its configuration 2 lessons · ~1 h 15 · then its quiz
2

Frame and secure a coding agent

2 skills
See the 2 skills
- Frame Claude Code with CLAUDE.md, targeted rules and settings.json 4 lessons · ~2 h 35 · then its quiz
- Confine Claude Code's execution: permissions, secrets and sandbox 3 lessons · ~2 h 15 · then its quiz
3

Extend and industrialize a coding agent

4 skills
See the 4 skills
- Automate and extend Claude Code with hooks, skills and plugins 6 lessons · ~4 h 30 · then its quiz
- Connect an MCP server to Claude Code and delegate to isolated subagents 2 lessons · ~1 h 20 · then its quiz
- Run Claude Code without an interactive session, in CI, with the right model and cost 2 lessons · ~1 h 25 · then its quiz
- Deliver a complete project driven by Claude Code, one vertical slice at a time 1 lesson · ~1 h 00 · then its quiz
4

Understand, serve and integrate language models

5 skills
See the 5 skills
- Explain how an LLM works, its inference and its quantization 4 lessons · ~2 h 20 · then its quiz
- Write reliable prompts: roles, few-shot, Chain-of-Thought and ReAct 2 lessons · ~2 h 10 · then its quiz
- Run and serve an open source LLM, from the workstation to the GPU 7 lessons · ~5 h 45 · then its quiz
- Call an LLM from Python: completion, streaming, conversation, structured output and images 5 lessons · ~4 h 35 · then its quiz
- Operate an LLM gateway: routing, fallback, cache, keys and budgets 2 lessons · ~2 h 20 · then its quiz
5

Build a RAG

3 skills
See the 3 skills
- Prepare a corpus for RAG: extract, clean, chunk 4 lessons · ~2 h 40 · then its quiz
- Embed a corpus and index it in a vector database 6 lessons · ~4 h 30 · then its quiz
- Build an end-to-end RAG, make its retrieval reliable and take it to production 6 lessons · ~4 h 25 · then its quiz
6

Build and industrialize MCP servers

2 skills
See the 2 skills
- Build an MCP server and client in Python 6 lessons · ~3 h 45 · then its quiz
- Secure, test, authenticate and deploy MCP servers 5 lessons · ~4 h 20 · then its quiz
7

Build AI agents

3 skills
See the 3 skills
- Build a tool-using AI agent: ReAct loop, function calling and typed output 4 lessons · ~3 h 05 · then its quiz
- Orchestrate agents with a state graph: LangGraph, multi-agent, memory, patterns and MCP 5 lessons · ~4 h 10 · then its quiz
- Have an agent run code in a hardened sandbox 2 lessons · ~1 h 35 · then its quiz
8

Assemble, observe and secure a sovereign AI stack

3 skills
See the 3 skills
- Assemble a sovereign AI stack and expose it behind a secured web interface 5 lessons · ~4 h 05 · then its quiz
- Trace LLM calls with OpenTelemetry GenAI up to Grafana Tempo 2 lessons · ~1 h 15 · then its quiz
- Analyze an LLM application's risks with the OWASP Top 10 for LLM 2025 and choose defense-in-depth controls 1 lesson · ~45 min · then its quiz

The domain's steps

Work with a coding agent

Frame and secure a coding agent

Extend and industrialize a coding agent

Understand, serve and integrate language models

Build a RAG

Build and industrialize MCP servers

Build AI agents

Assemble, observe and secure a sovereign AI stack