The Resolve AI prompt library offers practical examples illustrating how engineers can leverage Resolve AI for various technical challenges. Among the key areas highlighted, the library addresses incident resolution, cost optimization, and development contexts. For instance, one prompt focuses on fixing deployment failures, providing guidance on debugging issues related to deployment and image regressions. Another example targets frontend errors, where engineers can learn to investigate errors across multiple services, enhancing their troubleshooting efficiency. API performance is also a concern, with a prompt dedicated to identifying slowdowns and tracing them back to specific code changes, which is vital for maintaining application responsiveness. The library includes resources for designing a multi-tenant rate limiter, crucial for managing traffic in production environments. Onboarding processes are also featured, with prompts for both Kafka and Kubernetes. These guides help engineers understand cluster infrastructure and resource allocation, ensuring they can effectively utilize these technologies in live settings. Lastly, there’s a focus on optimizing EC2 instances by analyzing CPU utilization in EKS worker nodes to prevent over-provisioning, which can lead to unnecessary costs.