Generative AI Leader
In this course, you will take a journey from a broad overview of gen AI to understanding how to leverage gen AI and Google Cloud for organizational transformation.
2 d
Fundamental
CLAUDECODE100
Claude Code Training
Become an augmented developer by mastering Claude Code, Anthropic's CLI tool for AI-assisted development. This intensive one-day training teaches you to collaborate effectively with AI agents: context management with CLAUDE.md, planning with Plan Mode, test generation, sub-agent orchestration and creating reusable skills. Participants leave with concrete methods and workflows directly applicable to their projects.
✓ Official training SFEIR InstituteLevel Fundamentals⏱️ 1 day (7h)
What you will learn
- Explain the augmented developer concept and distinguish augmented development from vibe coding.
- Create effective CLAUDE.md context files to guide Claude Code behavior according to project conventions.
- Apply the Plan Mode workflow to review and approve AI-proposed refactorings before execution.
- Generate unit and integration tests with Claude Code achieving significant coverage (>=70%).
- Create autonomous sub-agents and reusable skills to automate repetitive workflows.
- Orchestrate multiple sub-agents in parallel and sequential patterns for complex tasks.
- Master essential commands and productivity tips for Claude Code.
Prerequisites
- Practical mastery of at least one programming language (Python, JavaScript, Java, TypeScript, Go...).
- Daily experience with Git and a modern IDE (VS Code, IntelliJ, WebStorm, etc.).
- Basic command-line and file editing skills.
- A standard laptop (16 GB recommended) with rights to install software.
- Recent operating system (Windows 10+, macOS 10.15+, Linux).
- Git installed and configured with access to GitHub/GitLab.
- Recent version of Node.js and npm installed and configured.
- A stable internet connection.
Target audience
- Software developers (backend, frontend, full-stack) looking to integrate Claude Code into their daily workflow., Tech Leads and architects seeking to evaluate and adopt AI-augmented development for their teams., DevOps and Platform Engineers interested in advanced automation with AI agents.
Training Program
6 modules to master the fundamentals
Objectives
- Explain the augmented developer concept and distinguish it from AI replacement narratives
- Identify tasks suited for AI delegation (refactoring, documentation, tests)
- Classify scenarios by AI suitability (autonomous, collaborative, human-directed)
- Articulate appropriate verification steps for AI-generated code
Topics covered
- →The augmented developer: a new paradigm for software development
- →Key principles: delegation, supervision, collaboration, trust with verification
- →Traditional vs augmented developer: comparing roles and workflows
- →Addressing common concerns about AI-generated code
- →AI capabilities matrix: autonomous, partnership, human-directed
- →Realistic expectations: what AI does well and struggles with in 2026
- →Vibe Coding vs Augmented Development: definitions, limits and when it's acceptable
- →Trust but always verify: automated and human verification
Activities
Quiz: augmented developer role, workflows, trust and AI delegation
Objectives
- Install and configure Claude Code on your workstation
- Choose the authentication method suited to your context
Topics covered
- →Installation methods: native (recommended), Homebrew, npm
- →Native installation on Windows (PowerShell, CMD), WSL, macOS and Linux
- →OS-specific considerations: WSL vs Git Bash on Windows
- →Authentication: OAuth (recommended) and API key
- →Environment integration: PATH, verification
- →IDE integration: JetBrains (IntelliJ, PyCharm)
Objectives
- Create effective CLAUDE.md files using the six-section template
- Apply the Plan Mode workflow for multi-file refactorings
- Generate unit and integration tests with >=70% coverage
- Evaluate when to use Plan Mode vs Direct Execution
Topics covered
- →CLAUDE.md: persistent context file for Claude Code
- →Six-section template: Project Overview, Architecture, Directory Structure, Coding Conventions, Development Workflow, Context for AI
- →Concrete examples per section and best practices
- →Without CLAUDE.md vs With: impact on generated code quality
- →Plan Mode: review-before-execution workflow in three phases (Request → Review → Execute)
- →Making effective requests and review checklist
- →Approve, modify or reject a plan
- →Test generation: three patterns (unit, integration, improvement)
- →Quality principles: AAA structure, descriptive names, mocking external dependencies
Activities
Lab 1-1: Create a CLAUDE.md and verify context usage
Lab 1-2: Refactoring with Plan Mode (analysis, plan, review, validation)
Lab 1-3: Unit and integration test generation
Quiz: CLAUDE.md impact, Plan Mode vs Direct Execution, coverage vs quality
Objectives
- Understand how Claude Code's agentic loop works
- Organize project documentation into structured .md files for efficient context management
- Implement modular rules in .claude/rules/ for large codebases
- Apply advanced context management techniques
Topics covered
- →The agentic loop: Perceive (Read) → Reason → Act
- →Claude Code models: Sonnet 4.6 (default), Opus 4.6, Haiku 4.5
- →Available tools: files, terminal, search, web
- →Access control and permissions: reads, modifications, dangerous commands
- →Sessions and context: ephemeral sessions, context management, parallelization
- →Structured documentation: from monolithic CLAUDE.md to docs/ by concern
- →CLAUDE.md as reference hub with selective context loading
- →Modular rules: organization in .claude/rules/ with subfolders
- →Loading hierarchy: enterprise, project, rules, user, local
- →Unconditional rules vs path-specific rules (YAML frontmatter paths)
Activities
Lab 2-1: Structured documentation organization with selective loading
Lab 2-2: Creating modular rules with YAML frontmatter paths
Quiz: agentic loop, monolithic CLAUDE.md, monorepo, docs vs rules
Objectives
- Create autonomous sub-agents with specialized contexts and tool permissions
- Orchestrate multiple sub-agents in parallel and sequential patterns
- Distinguish between sub-agents (isolation) and skills (automation)
- Build custom skills to automate repetitive workflows
Topics covered
- →Sub-agents: separate context, limited tools, specialized prompt, independent permissions
- →Built-in agents: Explore (Haiku), Plan (Sonnet), General-purpose (Sonnet), Bash (Sonnet)
- →Creating a custom sub-agent with YAML frontmatter in .claude/agents/
- →Project vs user storage and delegation modes (automatic vs explicit)
- →Skills: automating repetitive workflows with .claude/skills/*/SKILL.md
- →Skill anatomy: YAML frontmatter, $ARGUMENTS, manual vs automatic invocation
- →Skill types: Reference (knowledge) vs Task (action)
- →Sub-agents vs Skills: key differences (context, tools, model, performance)
- →Pattern 1: Parallel search (3 simultaneous agents)
- →Pattern 2: Agent chaining (exploration → review → fix → validation)
- →Pattern 3: Volume operation isolation
- →Advanced orchestration: foreground vs background, combining sub-agents + skills
Activities
Lab 3-1: Creating a custom sub-agent with tool restrictions
Lab 3-2: Creating custom skills for repetitive workflows
Lab 3-3: Multi-agent orchestration (parallel and chaining)
Quiz: sub-agent vs skill, file scanning, automation, parallelization
Objectives
- Master essential Claude Code commands for daily productivity
- Apply workflow optimization techniques
Topics covered
- →CLI commands: startup, sessions, print mode, updates
- →Interactive commands: /resume, /rename, /clear, /compact, /context, /memory, /cost, /stats
- →Checkpointing and rewind: restoring conversation, code, or both
- →Bash commands (! prefix) and background mode (Ctrl+B)
- →Workflow best practices and context optimization
Activities
Quiz: session resume, rewind, background mode, saturated context
Related Trainings
Tendance
Introduction to AI and Machine Learning on Google Cloud
This course introduces the AI and machine learning (ML) offerings on Google Cloud that build both predictive and generative AI projects. It explores the technologies, products, and tools available throughout the data-to-AI life cycle, encompassing AI foundations, development, and solutions. It aims to help data scientists, AI developers, and ML engineers enhance their skills and knowledge through engaging learning experiences and practical hands-on exercises.
1 d
Fundamental
Introduction to Developer Efficiency with Gemini on Google Cloud
Generative AI is now at the center of transforming how software is designed, built, run, and managed. For developers, generative AI is a powerful tool for making coding more efficient and using APIs, such as the Gemini and PaLM APIs, within their applications. In this course, you are introduced to how generative AI can be used to make developers more efficient at writing code and implementing new features into applications. You will also explore available models in Vertex AI Model Garden.
1 d
Fundamental
Upcoming sessions
No date suits you?
We regularly organize new sessions. Contact us to find out about upcoming dates or to schedule a session at a date of your choice.
Register for a custom dateQuality Process
SFEIR Institute's commitment: an excellence approach to ensure the quality and success of all our training programs. Learn more about our quality approach
Teaching Methods Used
- Lectures / Theoretical Slides — Presentation of concepts using visual aids (PowerPoint, PDF).
- Technical Demonstration (Demos) — The instructor performs a task or procedure while students observe.
- Guided Labs — Guided practical exercises on software, hardware, or technical environments.
- Quiz / MCQ — Quick knowledge check (paper-based or digital via tools like Kahoot/Klaxoon).
Evaluation and Monitoring System
The achievement of training objectives is evaluated at multiple levels to ensure quality:
- Continuous Knowledge Assessment : Verification of knowledge throughout the training via participatory methods (quizzes, practical exercises, case studies) under instructor supervision.
- Progress Measurement : Comparative self-assessment system including an initial diagnostic to determine the starting level, followed by a final evaluation to validate skills development.
- Quality Evaluation : End-of-session satisfaction questionnaire to measure the relevance and effectiveness of the training as perceived by participants.
Train multiple employees
- Volume discounts (multiple seats)
- Private or custom session
- On-site or remote