Get in Touch

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

  • A solid understanding of software development principles and standard engineering workflows.
  • Experience with a programming language such as JavaScript, Python, etc.
  • Proficiency in command line/terminal usage and familiarity with Git workflows.

Audience

  • Software developers looking to integrate AI into their development process.
  • Technical team leads aiming to boost engineering productivity with AI tools.
  • DevOps engineers and engineering managers interested in AI-assisted coding automation.
 21 Hours

Number of participants


Price per participant

Testimonials (1)

Upcoming Courses

Related Categories