Introduction
AI-assisted coding uses large language models (LLMs) to help you write, review, debug, and refactor code.
Who This Is For
- Anyone curious about the practical side of AI-assisted development
- Developers looking to integrate AI tools into their workflow
- Teams evaluating AI coding assistants
What You'll Learn
- Core Concepts Tokens, context windows, temperature, system prompts, and tool use
- Tools & Workflows Setting up and using AI tools in your development environment
- Prompt Engineering How to communicate effectively with AI coding tools
- Best Practices Writing reliable software with AI assistance
- Exercises Hands-on practice applying AI-assisted coding techniques to a dummy problem
Outcomes
After working through this documentation, you should be able to:
- Explain how tokens, context windows, and system instructions affect model behavior
- Prompt coding agents with clear constraints and verifiable done criteria
- Run safer AI-assisted workflows with checkpoints, tests, and code review
- Choose tools and execution modes based on the task, risk, and level of autonomy needed
Getting Started
Start with Core Concepts to understand how AI coding tools work under the hood, then explore Tools & Workflows to set up your environment and Prompt Engineering to learn how to get the most out of your AI tools. When you're ready to put it all together, try the Exercises for hands-on practice.
Suggested Learning Paths
| Audience | Start Here | Then Read |
|---|---|---|
| New to AI coding tools | Core Concepts | Prompt Engineering -> Best Practices |
| Working developers adopting tools now | Tools & Workflows | Best Practices -> Exercises |
| Team leads and enablement owners | Best Practices | Tools & Workflows -> Core Concepts |
Sources: Claude Code overview, OpenAI platform overview, Gemini API docs