Course Outline
09:00 – 09:15 — Welcome & Overview
- Clarification of daily objectives, technical environment verification, and participant introductions
09:15 – 10:00 — Module 1: AI Code Quality & the Plan–Execute–Review Principle
- Identifying the five critical determinants of output quality: model selection, codebase context, tooling, prompt precision, and workflow design
- Understanding why decoupling planning, execution, and review phases yields superior results compared to a single-prompt approach
- Establishing 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
- Differentiating Claude Code from Copilot, Cursor, and chat-based utilities, and explaining the significance of these distinctions
- Exploring the agentic cycle: reading, planning, acting, and verifying
- Demonstrating how to steer a multi-file task from a single instruction
10:45 – 12:15 — Module 3: Setup & Personalisation: CLAUDE.md, Skills, Hooks, Agents & MCP
- Using CLAUDE.md to encode project memory, architectural rules, and team standards
- Implementing skills and hooks to create reusable slash-command workflows and event-driven automation
- Examining sub-agents: how Claude Code internally manages parallel work delegation
- Leveraging MCP to integrate external tools—such as GitHub, databases, and internal APIs—while defining security boundaries
- Practical exercise: configuring Claude Code and tailoring 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 defined acceptance criteria
- Iterating on outputs: determining when to approve results and when to issue corrective instructions
- Practical exercise: implementing a real feature from start to finish
13:45 – 14:45 — Case 2: Doing Code Review with Claude Code
- Structuring review delegations focusing on security, design, and performance
- Conducting multi-file reviews with full traceability—identifying changes, rationale, and verification points
- Practical exercise: reviewing actual code submissions from participants
14:45 – 15:45 — Case 3: Designing with Claude Code
- Generating architecture decisions and ADRs directly from requirements
- Exploring design alternatives and highlighting trade-offs
- Practical exercise: designing a component or feature using Claude Code
15:45 – 16:15 — Recap & Q&A
- Summarizing key takeaways and committing to three specific actions each participant will adopt
- Open floor for questions and discussion
Requirements
- Proficiency in at least one programming language
- Experience operating within a terminal or command-line interface
- Fundamental understanding of Git workflows (commits, branches, pull requests)
- A laptop with an active internet connection; a Claude Pro account is mandatory (setup instructions will be 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
