{"slug":"epilot-reduces-email-processing-time-by-87-using-amazon-bedrock","url":"https://findausecase.com/use-cases/epilot-reduces-email-processing-time-by-87-using-amazon-bedrock","title":"Epilot reduces email processing time by 87% using Amazon Bedrock","description":"Cologne, Germany-based Epilot, which provides an extended-relationship-management (XRM) platform for energy companies, built an AI email-summarization feature on Amazon Bedrock (Anthropic's Claude via serverless AWS Lambda/SQS architecture) that summarizes long customer email threads for its 170+ energy-sector customers. Epilot generates 55,000 AI email summaries monthly with a negligible failure rate; about 80% of users say the feature simplifies their work, and users save 87% of the time previously spent on email management. Epilot also built a 'suggested actions' feature that auto-updates customer records from email content with a human in the loop, and keeps all processed data within an EU AWS Region using Amazon Bedrock's zero-retention data policy.","company":"Epilot","industry":"Energy","country":"Germany","aiCapabilities":["Natural Language Processing","Generative AI"],"technology":["Amazon Bedrock","Anthropic Claude","AWS Lambda","Amazon SQS"],"deployment":"Public Cloud","problemStatement":"Communication is a central part of the workload in sales and services in the energy sector. Email chains quickly become lengthy and complex, costing employees time as they read through messages before recognizing what action is needed.","solutionApproach":"Epilot used generative AI to analyze entire email threads and summarize them into a few key points so sales or service employees can immediately recognize any action needed. It built the capability into its XRM's serverless architecture on AWS Lambda: an API sends a summarization request to Amazon SQS, which initiates a Lambda function that orchestrates the summarization task in Amazon Bedrock. After evaluating options with Amazon Bedrock Evaluations, Epilot chose Anthropic's Claude (Claude Sonnet) in Amazon Bedrock. It also built a 'suggested actions' feature that auto-updates customer records from email content, with a human in the loop to verify automatic actions.","businessValue":"Epilot generates 55,000 email summaries each month with a negligible failure rate. About 80 percent of Epilot's users say the feature simplifies their work, and users save 87 percent of the time previously spent on email management.","evidence":{"band":"high"},"sourceUrl":"https://aws.amazon.com/solutions/case-studies/epilot-genai-case-study","dates":{"publishedAt":"2026-08-21T09:06:33.831Z","publishedAtSource":"pipeline","updatedAt":"2026-08-21T09:06:33.831Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/epilot-reduces-email-processing-time-by-87-using-amazon-bedrock. Bulk republication requires permission."}