{"slug":"achieving-near-zero-downtime-and-powering-generative-ai-using-amazon-eks-with-ada","url":"https://findausecase.com/use-cases/achieving-near-zero-downtime-and-powering-generative-ai-using-amazon-eks-with-ada","title":"Achieving Near-Zero Downtime and Powering Generative AI Using Amazon EKS with Ada","description":"Customer service automation company Ada migrated its Kubernetes clusters to Amazon EKS and now runs a generative AI reasoning engine for customer conversations, raising automated resolution rates from 20-30 percent with its prior declarative agents to up to 77 percent.","company":"Ada Support Inc.","industry":"Technology & Software","aiCapabilities":["Conversational AI","Generative AI"],"technology":["Amazon EKS","AWS Global Accelerator","Amazon EC2 Spot Instances","AWS Graviton processor","Argo CD"],"deployment":"Public Cloud","problemStatement":"Ada's self-managed Kubernetes clusters (seven clusters with up to 700 nodes each) were complex and costly to maintain: two or three full-time engineers took up to 5 months to complete a Kubernetes version upgrade, and upgrades consumed up to 30% of the yearly error budget under a 99.9% availability SLA.","solutionApproach":"Ada migrated its self-managed Kubernetes clusters to Amazon EKS, using AWS Global Accelerator and a blue/green deployment strategy to incrementally route traffic with near-zero downtime, adopted GPU slicing for its ML inference workloads, used Argo CD to keep application sets in sync, and now runs a generative AI reasoning engine (using ML models and LLM calls) for its customer service automation product.","businessValue":"Ada cut compute costs 15%, increased compute efficiency 30%, increased GPU usage cost efficiency 20%, increased deployment velocity 70%, and cut Kubernetes upgrade time from up to 5 months to 5 days; its shift to a generative AI agent lifted automated resolution rates from 20-30% with declarative agents to up to 77%.","evidence":{"band":"high"},"sourceUrl":"https://aws.amazon.com/solutions/case-studies/ada-support-eks-case-study/","dates":{"publishedAt":"2026-10-06T05:47:32.743Z","publishedAtSource":"pipeline","updatedAt":"2026-10-06T05:47:32.743Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/achieving-near-zero-downtime-and-powering-generative-ai-using-amazon-eks-with-ada. Bulk republication requires permission."}