Claude Code in Action
Description
This course teaches developers how to work with Claude Code as a coding agent. How to use it to build features, write tests, refactor code, automate pipelines, and collaborate as a team. The course is specifically designed to allow participants learn how to leverage an AI coding agent effectively working with with the most popular technology stacks.
Indicative Duration: 16 training hours
*Duration is adjusted based on the final scope and the target audience.
Scope
| 1. Intro to Claude Code | • Claude Code vs. Copilot: a paradigm comparison • CLI setup and project configuration Lab: first delegated task |
| 2. Establishing Project Rules | • Context dependency and convention consistency • CLAUDE.md structure and best practices Lab: CLAUDE.md authoring and validation |
| 3. Claude Prompting | • Common prompting pitfalls • Four core prompt patterns Lab: iterative correction through dialogue |
| 4. Building Features | • Single-prompt multi-file generation capabilities • AI output review checklist Lab: full feature slice from a user story |
| 5. Testing & Refactoring | • Autonomous test strategy and coverage gap analysis • Codebase comprehension and impact analysis Lab: test suite generation and service refactoring |
| 6. Debugging Claude Code failures |
• Hallucination patterns in modern codebases • Task delegation and trust calibration framework Lab: error detection and correction exercise |
| 7. CI/CD, automation & Claude Code collaboration |
• GitHub Actions workflow generation • Claude Code SDK and automation recipes • Team conventions, shared CLAUDE.md, and review workflows Lab: pipeline generation and SDK automation |
| 8. Capstone Project / Challenge | • Team build challenge • Course retrospective and takeaways |
Learning Objectives
Upon completion of the course participants will be able to:
- Use Claude Code as a primary development tool, delegating tasks by intent
- Configure Claude Code for any project using CLAUDE.md so the agent respects team conventions automatically
- Apply proven prompt patterns to get consistent, production-quality output from the agent
- Generate complete feature slices from a single high-level prompt
- Use Claude Code to explore and understand unfamiliar codebases quickly
- Generate meaningful test suites and close coverage gaps through agent dialogue
- Identify and correct hallucinations and errors in AI-generated Java code
- Design lightweight team workflows and shared conventions for AI-assisted development
Target Audience
- Roles: Backend Developer, Engineering Manager, Full-Stack Developer, Software Architect, Software Developer, Technical Lead, Test Engineer, Data Engineer, Quality Assurance Engineer
- Seniority: Mid-Level to Senior Professionals
Prerequisite Knowledge
- Comfortable writing code in any modern technology stack, ideally having hands-on experience
- Basic Git workflow (commit, branch, pull request)
- No prior experience with AI coding tools or prompt engineering required
Delivery Method
Sessions can be delivered via the following formats:
- Live Online – Interactive virtual sessions via video conferencing
- On-Site – At your organization’s premises
- In-Person – At Code.Hub’s training center
- Hybrid – A combination of online and in-person sessions
