Course Outline
09:00 – 09:15 — Welcome & Overview
- Setting the day's objectives, verifying technical setup, and participant introductions
09:15 – 10:00 — Module 1: AI Code Quality & the Plan–Execute–Review Principle
- Five key factors influencing outcomes: model selection, codebase context, tooling integration, prompt precision, and workflow design
- The benefits of separating planning, execution, and review phases compared to relying on a single prompt
- A decision-making framework to guide the remainder of the day
10:00 – 10:45 — Module 2: From Autocomplete to Agent: The Claude Code Paradigm
- Understanding how Claude Code differs from Copilot, Cursor, and other chat-based tools — and why this distinction is critical
- The agentic lifecycle: 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 internal delegation
- MCP: connecting external tools (such as GitHub, databases, and internal APIs) while maintaining security boundaries
- Hands-on exercise: configuring Claude Code and personalizing your setup
12:15 – 12:45 — Lunch Break
12:45 – 13:45 — Case Study 1: Writing Code with Claude Code
- Delegating implementation tasks by providing clear context and acceptance criteria
- Iterating on results: determining when to accept output versus when to redirect the agent
- Hands-on exercise: implementing a real feature from start to finish
13:45 – 14:45 — Case Study 2: Conducting Code Review with Claude Code
- Structuring review delegations focused on security, design patterns, and performance
- Conducting multi-file reviews with full traceability — understanding what changed, why it matters, and what to verify
- Hands-on exercise: reviewing actual code submitted by participants
14:45 – 15:45 — Case Study 3: Designing with Claude Code
- Generating architectural decisions and Architecture Decision Records (ADRs) based on requirements
- Exploring design alternatives and identifying potential trade-offs
- Hands-on exercise: designing a component or feature using Claude Code
15:45 – 16:15 — Recap & Q&A
- Key takeaways and each participant’s commitment to three concrete action items
- Open question-and-answer session
Requirements
- Substantial experience in at least one programming language
- Comfort with working in a terminal or command-line environment
- Foundational knowledge of Git (including commits, branches, and pull requests)
- A laptop with internet access and an active Claude Pro account (registration instructions will be provided)
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
