Course Outline
09:00 – 09:15 — Welcome & Overview
- Day objectives, verification of technical infrastructure, and participant introductions
09:15 – 10:00 — Module 1: AI Code Quality & the Plan–Execute–Review Principle
- The five determinants of output quality: model selection, codebase context, tooling, prompt precision, and workflow design
- Rationale for separating planning, execution, and review processes to enhance outcomes beyond single-prompt interactions
- A decision-making framework applicable throughout the remainder of the session
10:00 – 10:45 — Module 2: From Autocomplete to Agent: The Claude Code Paradigm
- Differentiation of Claude Code from Copilot, Cursor, and chat-based interfaces—and the operational significance of these distinctions
- The agentic operational cycle: read, plan, act, verify
- Live demonstration: executing a multi-file task from a singular instruction set
10:45 – 12:15 — Module 3: Setup & Personalisation: CLAUDE.md, Skills, Hooks, Agents & MCP
- CLAUDE.md: encoding project memory, architectural standards, and team conventions
- Skills and hooks: establishing reusable slash-command workflows and event-driven automation
- Sub-agents: mechanisms for internal delegation of parallel workloads
- MCP: integration of external tools—including GitHub, databases, and internal APIs—with defined security boundaries
- Hands-on: configuring Claude Code and customizing the setup for specific requirements
12:15 – 12:45 — Lunch Break
12:45 – 13:45 — Case 1: Writing Code with Claude Code
- Delegating implementation tasks with defined context and acceptance criteria
- Iterating on results: criteria for acceptance versus redirection
- Hands-on: end-to-end implementation of a functional requirement
13:45 – 14:45 — Case 2: Doing Code Review with Claude Code
- Structuring review delegation across security, design, and performance domains
- Multi-file review with traceability—documenting changes, rationale, and verification points
- Hands-on: review of actual code submissions from participants
14:45 – 15:45 — Case 3: Designing with Claude Code
- Generating architecture decisions and ADRs from stated requirements
- Exploring design alternatives and identifying trade-offs
- Hands-on: design of a component or feature utilizing Claude Code
15:45 – 16:15 — Recap & Q&A
- Key takeaways and three specific actionable commitments from each participant
- Open Q&A session
Requirements
- Proficient experience in at least one programming language
- Familiarity with terminal / command-line environments
- Basic proficiency in Git (commits, branches, pull requests)
- Laptop with internet connection — Claude Pro account required (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
