Introduction to the AI Co-Pilot
Learn about the AI-driven development methodology at the heart of VibeFast.
VibeFast is more than just a template; it's an AI-driven development environment. At its core is the VibeFast AI Co-Pilot, a system designed to turn your Large Language Model (LLM) of choice—be it ChatGPT, Claude, or a tool like Cursor—into an expert on your codebase.
What is the AI Co-Pilot?
The Co-Pilot is not a separate piece of software. It is a methodology powered by a collection of expert-level prompts located in the /prompts directory of your project.
Each file in this directory is a carefully crafted set of rules, guidelines, and examples that teaches an AI how to perform a specific, high-quality task that is perfectly aligned with VibeFast's architecture and coding standards.
Think of it like this: Instead of giving the AI a simple instruction like "write a component," you give it the VibeFast prompt and your instruction. The prompt acts as a "brain" or "expert context" for the AI, ensuring the code it produces is exactly what you need.
Why Use This Method?
- Consistency: The AI will always follow the project's coding standards, naming conventions, and architectural patterns.
- Quality: The prompts enforce best practices, such as creating accessible components or writing thorough unit tests.
- Speed: It dramatically accelerates development by automating repetitive and complex tasks. You spend less time writing boilerplate and more time building features.
The /prompts Directory
Here are some of the key prompts included in VibeFast:
write-unit-tests.md
A comprehensive guide that teaches the AI how to write high-quality unit tests using Jest and React Native Testing Library, including how to mock all necessary dependencies.
image-to-components.md
Instructs the AI to analyze an image of a UI and generate a React Native component that matches the design, using NativeWind for styling.
expo-doctor.md
A specialized prompt that helps the AI diagnose and fix dependency issues by running expo doctor and interpreting its output.
In the next section, we'll walk through exactly how to use these prompts to start building with your AI Co-Pilot.