Course Outline
09:00 – 09:15 — Welcome & Overview
- Day’s objectives, technical setup verification, and participant introductions
09:15 – 10:00 — Module 1: AI Code Quality & the Plan–Execute–Review Principle
- The five key levers influencing outcomes: model selection, codebase context, tooling, prompt precision, and workflow design
- Why separating planning, execution, and review phases delivers superior results compared to single-prompt approaches
- A decision framework to guide activities throughout the day
10:00 – 10:45 — Module 2: From Autocomplete to Agent: The Claude Code Paradigm
- How Claude Code differs from Copilot, Cursor, and chat-based tools—and why this distinction matters
- The agentic cycle: read, plan, act, verify
- Live demo: executing a multi-file task from a single instruction
10:45 – 12:15 — Module 3: Setup & Personalisation: CLAUDE.md, Skills, Hooks, Agents & MCP
- CLAUDE.md: encoding project memory, architecture rules, and team conventions
- Skills and hooks: building reusable slash-command workflows and event-driven automation
- Sub-agents: understanding how Claude Code internally delegates parallel work
- MCP: connecting external tools (GitHub, databases, internal APIs) while establishing security boundaries
- Hands-on exercise: configure Claude Code and personalise your environment
12:15 – 12:45 — Lunch Break
12:45 – 13:45 — Case 1: Writing Code with Claude Code
- Delegating implementation tasks with clear context and acceptance criteria
- Iterating on outputs: knowing when to accept results and when to redirect
- Hands-on exercise: implement a real feature end-to-end
13:45 – 14:45 — Case 2: Conducting Code Reviews with Claude Code
- Structuring review delegations covering security, design, and performance aspects
- Multi-file reviews with traceability—tracking changes, rationale, and verification steps
- Hands-on exercise: review actual code submitted by participants
14:45 – 15:45 — Case 3: Designing Solutions with Claude Code
- Generating architecture decisions and Architecture Decision Records (ADRs) from requirements
- Exploring design alternatives and identifying trade-offs
- Hands-on exercise: design a component or feature using Claude Code
15:45 – 16:15 — Recap & Q&A
- Key takeaways and three concrete action items each participant commits to implementing
- Open floor for questions
Requirements
- Proven proficiency in at least one programming language
- Comfort navigating terminal or command-line interfaces
- Familiarity with Git fundamentals (commits, branches, pull requests)
- Laptop with internet access – a Claude Pro account is mandatory (setup instructions provided upon registration)
Testimonials (3)
Using Claude Code in a more efficient way
Virgil Trif - Frequentis
Course - Claude Code: Agentic AI Development · 1-Day
claude mcp, how to promote and sell AI created software
Precup Andrei - Frequentis
Course - Claude Code: Agentic AI Development · 1-Day
The workshop to build an app