Agentic Workshop
Complete program

From zero to a complete agentic system

One conceptual foundation, ten operational modules, 48 lessons and 11 labs. Follow the path in order or open exactly what you need.

  1. 00
    85 min · 8 lessons

    Before Claude Code: AI, LLM, agents and tools

    Explain in your own words what an LLM and an agent are, recognize tools and permissions and design a first simulated local micro-mission with boundaries and tests.

    • The map: AI, machine learning, LLM and Claude Code
    • How a response is generated: tokens, probabilities, and limits
    • Prompt, context, window and memory are not the same thing
    • Hallucinations, uncertainty and evidence
    • From chatbot to agent: who decides and who acts
    • Tools, permissions and security boundaries
    • Files, folders, the terminal, and Git: your workspace
    • The first guided mission, from observation to test
  2. 01
    45 min · 4 lessons

    Thinking in an agentic way

    Turn a vague request into a testable assignment, with explicit boundaries and evidence.

    • From response to workflow
    • The operational assignment
    • Autonomy proportionate to risk
    • Evidence beats certainty of tone
  3. 02
    50 min · 4 lessons

    Environment, access and first program

    Navigate between terminal, editor, web and API, diagnose the environment and run the first script.

    • Four surfaces, different responsibilities
    • Read the terminal without fear
    • Credentials and environment variables
    • The first execution–error–correction cycle
  4. 03
    60 min · 4 lessons

    Exploring, Fixing, Refactoring, and Using Git

    Follow a bug from reproduction to commit, keeping the change small and verifiable.

    • Build a map before editing
    • From symptom to hypothesis
    • Bug fixes and refactoring are not synonymous
    • Git as a readable safety net
  5. 04
    55 min · 4 lessons

    Context engineering, memory and planning

    Build a small and reliable context, separating stable rules, memory, references and plan.

    • Four practical sources of context
    • Project instructions that really help
    • Compact without losing the contract
    • Plan before execution
  6. 05
    55 min · 4 lessons

    Reusable commands, Skills, and plugins

    Choose the correct level of reuse and define tools with clear inputs, permissions, outputs and tests.

    • Built-in Commands, Skills and Plugins
    • Input and output before instructions
    • Anatomy and test of a skill
    • Provenance and permissions
  7. 06
    55 min · 4 lessons

    MCP: Connect tools and sources

    Design a local or remote MCP connection with verifiable capabilities and least privilege.

    • Clients, servers, tools, resources and prompts
    • Local or remote: a trust decision
    • Minimum scope and tokens
    • Handshake, minimal test, and diagnosis
  8. 07
    50 min · 4 lessons

    Hooks and controlled local automation

    Design pre- and post-hooks that are deterministic, observable, and recoverable.

    • The life cycle of an event
    • Pre-hook: Secure the boundary
    • Post-hook: observe what has already happened
    • Idempotence, recursion and failure
  9. 08
    65 min · 4 lessons

    Specialized agents and collaboration

    Decompose a result, assign ownership and use parallelism only when it really saves time.

    • Decompose by result, not by label
    • Dependencies and real parallelism
    • File ownership and conflicts
    • Evidence-based synthesis
  10. 09
    60 min · 4 lessons

    Non-interactive CLI, JSON, and pipelines

    Build a reproducible local stream with structured output, gates and limited permissions.

    • Interactive and non-interactive
    • JSON as contract, not decoration
    • Gate and failure propagation
    • Auto mode and operating range
  11. 10
    65 min · 4 lessons

    Remote sessions, asynchronous routines and final project

    Design an asynchronous routine with checkpointing, limited retry, approval, and observable recovery.

    • The state of a session
    • Idempotent schedules
    • Remote control and human checkpoints
    • Capstone: full system, not full autonomy

The program is free. Your progress is yours.

Register to open labs, quizzes and exercises and recover all your progress online.

Create your free account