Course Outline
Introduction to Claude Code & AI-Assisted Software Engineering
- What Claude Code is and how it differs from traditional AI tools
- The role of generative AI agents in software engineering
- Using large prompts to build entire applications
- Understanding productivity gains from AI-assisted development
AI Labor & Software Engineering Productivity
- Treating Claude Code as an AI development team
- Addressing common fears and misconceptions about AI in engineering
- Understanding AI labor economics
- Leveraging the Best-of-N pattern to generate multiple solutions
- Selecting and refining optimal implementations
Claude Code, Design, and Code Quality
- Evaluating whether AI can judge code quality
- Applying software design principles with AI assistance
- Using AI to explore requirements and solution spaces
- Rapid prototyping with conversational design workflows
- Applying constraints and structured prompts to improve output quality
Process, Context, and the Model Context Protocol (MCP)
- The importance of process and context over raw code generation
- Global persistent context using CLAUDE.md
- Structuring project rules, architecture, and constraints in context files
- Reusable targeted context through Claude Code commands
- In-context learning by teaching Claude Code with examples
Automation & Documentation with Claude Code
- Using Claude Code to generate and maintain documentation
- Automating repetitive engineering tasks
- Creating reusable workflows driven by context and commands
Version Control & Parallel Development with Claude Code
- Integrating Claude Code with Git-based workflows
- Using Git branches and worktrees with AI agents
- Running Claude Code tasks in parallel
- Coordinating multiple AI subagents on separate features
- Managing parallel feature development safely
Scaling Claude Code & AI Reasoning
- Acting as Claude Code’s hands, eyes, and ears
- Ensuring Claude Code reviews and checks its own work
- Managing token limits and architectural complexity
- Designing project structure and file naming for AI scalability
- Maintaining long-term codebase health with AI assistance
Multimodal Prompting & Process-Driven Development
- Fixing process and context before fixing code
- Translating informal inputs (notes, sketches, specs) into production code
- Using multimodal inputs to guide implementation
- Creating repeatable AI-assisted development processes
Capstone: Defining Your Claude Code Process
- Designing a personal or team-level Claude Code workflow
- Combining context files, commands, subagents, and prompts
- Creating a reusable, scalable AI-assisted engineering process
Requirements
- An understanding of software development principles and common engineering workflows.
- Experience with a programming language such as JavaScript, Python, etc.
- Command line / terminal usage experience and familiarity with Git workflows.
Audience
- Software developers seeking to integrate AI into their development process.
- Technical team leads aiming to improve engineering productivity with AI tools.
- DevOps engineers and engineering managers interested in AI-assisted coding automation.
Delivery Options
Private Group Training
Our identity is rooted in delivering exactly what our clients need.
- Pre-course call with your trainer
- Customisation of the learning experience to achieve your goals -
- Bespoke outlines
- Practical hands-on exercises containing data / scenarios recognisable to the learners
- Training scheduled on a date of your choice
- Delivered online, onsite/classroom or hybrid by experts sharing real world experience
Private Group Prices RRP from £5700 online delivery, based on a group of 2 delegates, £1800 per additional delegate (excludes any certification / exam costs). We recommend a maximum group size of 12 for most learning events.
Contact us for an exact quote and to hear our latest promotions
Public Training
Please see our public courses
Testimonials (1)
Lecturer's knowledge in advanced usage of copilot & Sufficient and efficient practical session