Normalized claim
Time: 87% decrease
Users save 87% of their time on email management.
Epilot Reduces Email Processing Time by 87% Using Amazon Bedrock
Use case typeLegal document summarizationUpdated Jun 13, 2026
Epilot, based in Cologne, Germany, provides an XRM solution for the energy industry that helps energy suppliers, municipal utilities, grid operators, and solution providers simplify, digitize, and scale operations. The company built a serverless AWS architecture to summarize long email threads, helping sales and service teams quickly identify needed actions in complex customer communications.
- Organization
- Epilot
- Industry
- Energy & Utilities
- Location
- Germany
- Published
- May 2026
Reported outcomes
−87%
timeTime & speed
80%quantified impact
Strategic outcomes
Speed & agilityLaunched an email summarization workflowNew product / capabilityExtended toward AI action extractionCustomer experience & trustSimplified customer communications handling
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Quantified impact: 80%
About 80% of users say the feature simplifies their work.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Epilot
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Solutions Case Study
Sales and service teams had to manually read long, complex email chains, slowing customer communications and operational processes
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 4
- 1Email Summarization
- 2Customer Service Automation
- 3Workflow Automation
- Sales and service teams had to manually read long, complex email chains, slowing customer communications and operational processes.
- Epilot needed a faster way to summarize email threads and surface the actions hidden in long message exchanges.
- Epilot built an event-driven email summarization workflow on AWS using Amazon Simple Queue Service, AWS Lambda, and Amazon Bedrock.
- The team used Amazon Bedrock Evaluations and human review of prompt versions to select Anthropic Claude Sonnet in Amazon Bedrock for the summarization use case.
- Epilot also began extending the workflow toward an AI agent that extracts structured data from email chains and suggests actions while keeping humans in the loop.
- Epilot generates about 55,000 email summaries per month.
- Users save 87% of their time on email management.
- About 80% of users say the feature simplifies their work.
- The MVP launched in about 2 months from concept to production.
Architecture
A serverless, event-driven workflow sends email summarization requests to Amazon SQS. An AWS Lambda function orchestrates the summarization in Amazon Bedrock. Epilot used Amazon Bedrock Evaluations with human rating of prompt versions to select Claude Sonnet. The architecture is designed for scalable production workloads and keeps humans in the loop for downstream actions.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: May 13, 2026Publisher: AWSEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Market context
AI patterns
Browse the catalog
Was this useful?
Community
Comments
Loading comments...