Course Outline
09:00 – 09:15 — Welcome & Overview
- Daily 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 decoupling planning, execution, and review yields superior results compared to single-prompt approaches
- A decision-making framework applicable throughout the day
10:00 – 10:45 — Module 2: From Autocomplete to Agent: The Claude Code Paradigm
- Distinguishing Claude Code from Copilot, Cursor, and chat-based tools — and understanding why this distinction is critical
- The agentic cycle: read, plan, act, verify
- Live demonstration: executing a multi-file task via 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: Building reusable slash-command workflows and event-driven automation
- Sub-agents: Understanding how Claude Code handles parallel work internally
- MCP: Connecting external tools (GitHub, databases, internal APIs) while maintaining security boundaries
- Hands-on: Configuring Claude Code and customizing your personal setup
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 results: knowing when to accept output and when to redirect the agent
- Hands-on: Implementing a real feature from start to finish
13:45 – 14:45 — Case 2: Performing Code Reviews with Claude Code
- Structuring review delegations covering security, design, and performance aspects
- Conducting multi-file reviews with full traceability — tracking changes, rationale, and verification points
- Hands-on: Reviewing actual code contributed by participants
14:45 – 15:45 — Case 3: Designing with Claude Code
- Generating architecture decisions and Architectural Decision Records (ADRs) from requirements
- Exploring design alternatives and identifying trade-offs
- Hands-on: Designing a component or feature using Claude Code
15:45 – 16:15 — Recap & Q&A
- Summary of key takeaways and three concrete action items each participant will commit to
- Open Q&A session
Requirements
- Strong proficiency in at least one programming language
- Comfort with terminal/command-line environments
- Fundamental Git knowledge (commits, branches, pull requests)
- Laptop with internet connectivity — a Claude Pro account is required (registration instructions will be sent separately)
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
