Course Outline
09:00 – 09:15 — Welcome & Overview
- Day objectives, technical setup verification, and introductions
09:15 – 10:00 — Module 1: AI Code Quality & the Plan–Execute–Review Principle
- The five key factors influencing outcomes: model selection, codebase context, tooling, prompt precision, and workflow design
- Why separating planning, execution, and review phases yields superior results compared to relying on a single prompt
- A decision-making framework to guide you 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 is critical
- The agentic cycle: read, plan, act, verify
- Live demonstration: 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, architectural rules, and team conventions
- Skills and hooks: creating reusable slash-command workflows and event-driven automation
- Sub-agents: understanding how Claude Code internally delegates parallel work
- MCP: connecting external tools — such as GitHub, databases, and internal APIs — while establishing security boundaries
- Hands-on exercise: configuring Claude Code and personalizing your development 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 generated results: knowing when to accept and when to redirect
- Hands-on exercise: implement a real feature end-to-end
13:45 – 14:45 — Case 2: Doing Code Review with Claude Code
- Structuring a review delegation focused on security, design, and performance
- Conducting multi-file reviews with traceability — identifying what changed, why it changed, and what to verify
- Hands-on exercise: reviewing actual code submitted by participants
14:45 – 15:45 — Case 3: Designing with Claude Code
- Generating architecture decisions and Architecture Decision Records (ADRs) from requirements
- Exploring design alternatives and surfacing trade-offs
- Hands-on exercise: designing 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 Q&A session
Requirements
- Substantial experience in at least one programming language
- Comfort working within a terminal or command-line environment
- Fundamental knowledge of Git (including commits, branches, and pull requests)
- A laptop with internet access; a Claude Pro account is required (instructions will be sent 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
