Arity Innovation & Technology Culture

What types of products or services does your engineering team work on/create? What problem are you solving for customers?

Arity’s insurance engineering segment builds data products specifically designed for insurance use cases. Our work helps insurers better understand driving behavior and risk, ultimately enabling smarter decisions and more personalized experiences for their customers. We process managing trillions of telematics data points that include trip events flowing in real time from connected devices and transforming that into insights that power risk models and mobility solutions. We also work on modernization initiatives, such as migrating legacy systems to cloud-native architectures, improving continuous integration/continuous delivery pipelines and enhancing observability and system documentation.

Tell us about a recent project where your team used AI as a tool. What was it meant to accomplish? How did you use AI to assist?

Recently, we’ve been using AI tools such as Cursor AI, Copilot, Claude and custom Model Context Protocol integrations within our development workflow to accelerate delivery and improve code quality.

What would that project have looked like if you didn’t have AI as a tool to use? How has AI changed the way you work, in general?

Without AI, the development process would have been slower and more manual, especially for debugging, documentation and test generation. Tasks like diagnosing complex build or deployment issues could have taken half a day or more, while writing extensive test cases or documentation would have required multiple team members.

AI tools have significantly: reduced time-to-resolution for production and build issues; increased test coverage and code quality, leading to more stable releases; improved onboarding for new developers through automated documentation; and enhanced productivity, allowing engineers to focus on higher-value design and architectural tasks instead of repetitive debugging or setup work. Overall, AI has changed the way we work by embedding intelligence directly into our development workflow.

The Impact of AI on Shukla's Team

• “Code generation and refactoring: Cursor helped in writing and optimizing Go and Python code, including automating test case generation and code completion."
• “Debugging and troubleshooting: AI quickly identified issues that would have otherwise taken hours to solve manually.
• “Documentation and knowledge transfer: AI-generated documentation has made it easier to onboard new team members by explaining system architecture, dependencies and workflows."
• “Automation with Jira and CI/CD: Through the MCP integration, AI agents could pull Jira stories, analyze the related repositories and automatically suggest code or configuration changes, significantly reducing manual effort.
• “Feature planning: We are in the process of using Cursor plan mode for initial feature planning and architecture sequencing, improving the overall design workflow.”