Automatic Data Seeding for Testing your Apps

This project is a Python-based agent that generates synthetic data modeled after an existing database. It first analyzes the structure and statistical properties of the stored information, identifying key attributes such as data types, distributions, and relationships between fields. It then generates new entries that maintain the patterns of the original dataset while ensuring all data remains synthetic and non-sensitive.

Using techniques such as rule-based constraints, probabilistic sampling, and structured formatting, the agent creates realistic datasets suitable for application testing, load simulations, and controlled experiments. It supports customization for specific formats, enforcing consistency in unique identifiers, categorical variables, and numerical ranges. The goal is to provide developers with a reliable and automated way to populate test environments with useful, structured data that behaves like real-world input without the risks of using actual production data.

For future iterations, the project could integrate AI-driven data augmentation techniques or pre-trained language models to enhance data variability and contextual accuracy.