Course Outline
09:00 – 09:15 — Welcome & Session Overview
- Outlining daily objectives, verifying technical readiness, and opening introductions
09:15 – 10:00 — Module 1: AI Code Quality & the Plan–Execute–Review Framework
- Five critical factors influencing output quality: model selection, codebase context, tooling, prompt clarity, and workflow design
- The rationale for separating planning, execution, and review phases to achieve superior results compared to single-prompt approaches
- A practical decision-making framework to apply throughout the remainder of the day
10:00 – 10:45 — Module 2: From Autocomplete to Agent: The Claude Code Approach
- Distinguishing Claude Code from Copilot, Cursor, and chat-based interfaces, and explaining the significance of these differences
- The agentic workflow cycle: reading, planning, acting, and verifying
- Live demonstration: executing a multi-file task from a single command
10:45 – 12:15 — Module 3: Configuration & Customization: CLAUDE.md, Skills, Hooks, Agents & MCP
- CLAUDE.md: Capturing project memory, architectural guidelines, and team standards
- Skills and hooks: Developing reusable slash-command workflows and implementing event-driven automation
- Sub-agents: Understanding how Claude Code internally delegates parallel tasks
- MCP: Integrating external tools such as GitHub, databases, and internal APIs, while defining security perimeters
- Practical exercise: Configuring Claude Code and customizing your personal environment
12:15 – 12:45 — Lunch Break
12:45 – 13:45 — Case Study 1: Authoring Code with Claude Code
- Delegating implementation tasks with specific context and clear acceptance criteria
- Refining outcomes: Determining when to accept results and when to redirect the agent
- Practical exercise: Building a real-world feature from start to finish
13:45 – 14:45 — Case Study 2: Conducting Code Reviews with Claude Code
- Structuring review delegations to cover security, design, and performance
- Performing 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 Study 3: Designing Solutions with Claude Code
- Generating architecture decisions and ADRs based on stated requirements
- Evaluating design alternatives and highlighting potential trade-offs
- Practical exercise: Designing a component or feature alongside Claude Code
15:45 – 16:15 — Summary & Q&A
- Highlighting key learnings and committing to three specific action items
- Open floor for questions and discussion
Requirements
- Proficiency in at least one programming language
- Confidence in navigating a terminal or command-line interface
- Familiarity with core Git concepts, including commits, branches, and pull requests
- A laptop with an active internet connection; a Claude Pro account is required (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
