Auto-Owners Insurance is a Fortune 500 company that provides automotive, home, life, and commercial insurance to nearly 3 million policyholders in 26 states. They have been headquartered in Lansing, Michigan since 1917, and are represented by 48,000 licensed agents.

Auto-Owners employs multiple software teams that develop applications in support of their operations and infrastructure. A major focus of Auto-Owners is in streamlining the analysis of their codebases to further optimize their software development process.

The Code Quality Intelligence System analyzes code quality and displays it through an interactive dashboard. Developers are provided with information on where their code is inefficient or buggy. Suggestions to improve their development process, as well as actionable fixes, are automatically generated for developers.

Our system connects to Auto-Owners’ software code and tracks key metrics such as code churn, pull request timing, bug frequency, and change failure rate. We use machine learning to predict trends and potential risks for each metric. The system highlights testing blind spots, bottlenecks, and provides documentation checks utilizing large language models.

By providing early warnings and data-driven recommendations, our system enables teams to improve their development process. Instead of reacting to failures after deployment, teams can now anticipate risk and improve the most vulnerable parts of their codebase and maintain delivery quality through our Code Quality Intelligence System.

Our website is built using Vite.js and FastAPI. It is containerized using Docker. Statistical data models are used to generate forecasts and large language models are used to generate test recommendations and documentation. Data is stored using a SQL database.