Course Outline
09:00 – 09:15 — Welcome & Overview
- Session objectives, technical environment verification, and introductions
09:15 – 10:00 — Module 1: AI Code Quality & the Plan–Execute–Review Principle
- Five critical factors influencing output quality: the model, codebase context, available tooling, prompt specificity, and workflow design
- The advantage of decoupling planning, execution, and review phases over relying on a single monolithic prompt
- A decision-making framework to guide the remainder of the workshop
10:00 – 10:45 — Module 2: From Autocomplete to Agent: The Claude Code Paradigm
- Distinguishing Claude Code from tools like Copilot, Cursor, and chat-based assistants, and why this architectural difference is significant
- The agentic workflow: reading, planning, acting, and verifying
- Live demonstration: managing a multi-file task via a single instruction
10:45 – 12:15 — Module 3: Setup & Personalisation: CLAUDE.md, Skills, Hooks, Agents & MCP
- CLAUDE.md: capturing project memory, architectural guidelines, and team conventions
- Skills and hooks: building reusable slash-command workflows and event-driven automations
- Sub-agents: understanding how Claude Code delegates parallel workloads internally
- MCP: integrating external systems such as GitHub, databases, and internal APIs, while defining security boundaries
- Practical exercise: configuring and personalizing your Claude Code environment
12:15 – 12:45 — Lunch Break
12:45 – 13:45 — Case 1: Writing Code with Claude Code
- Delegating implementation tasks with specific context and acceptance criteria
- Iterative refinement: determining when to accept results and when to redirect the agent
- 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 covering security, design, and performance aspects
- Conducting multi-file reviews with clear traceability: identifying changes, rationale, and verification points
- Practical exercise: reviewing actual code contributed by participants
14:45 – 15:45 — Case 3: Designing with Claude Code
- Deriving 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
- Summary of key takeaways and three specific actions each participant will implement
- Open floor for questions and discussion
Requirements
- Proficient experience in at least one programming language
- Confidence in navigating a terminal or command-line interface
- Familiarity with Git workflows, including commits, branching, and pull requests
- A laptop with internet access; a Claude Pro account is mandatory (setup 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
