What challenges did Travelers Insurance face before AI implementation?

Travelers needed to classify large volumes of service-request emails that often contained ambiguous language and PDF attachments. Manual processing consumed significant time and was difficult to scale for routine policy-service requests.

Source

Evidence: Low35/100

Travelers Insurance: Amazon Bedrock + Amazon Textract email classification automation

Use case typeIntelligent document processingUpdated Jun 13, 2026

Travelers Insurance receives millions of service-request emails each year, many with ambiguous content and PDF attachments. The company and AWS Generative AI Innovation Center built an AI-based email classification workflow to automate routing of these requests into 13 service request categories.

Organization: Travelers Insurance
Industry: Insurance
Location: United States
Published: January 2025

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Accuracy: 91%

AWS Machine Learning BlogJan 31, 2025Blog postInferred claimLow evidence strength

The classifier reached 91% accuracy, up from 68% before prompt engineering.

Normalized claim

Accuracy: 68%

AWS Machine Learning BlogJan 31, 2025Blog postInferred claimLow evidence strength

The classifier reached 91% accuracy, up from 68% before prompt engineering.

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Travelers Insurance
Provider: AWS
Maturity: Unknown
Linked source: AWS Machine Learning Blog

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 3

1Email classification
2Document processing automation
3Workflow automation

The solution used Anthropic Claude models on Amazon Bedrock as a foundation-model classifier with prompt engineering and few-shot examples.
Email body text was extracted, PDF attachments were split into pages, and Amazon Textract was used to extract text, entities, and table data from the page images.
The email text and Textract output were combined into a single prompt to classify each message into one of 13 categories.
The team iterated on prompts, condensed categories, and improved instructions to raise accuracy and produce explainable outputs.

Technologies

Amazon Bedrock Amazon Textract Anthropic Claude 3

Architecture

Raw emails were ingested, body text extracted, and any PDF attachments were rendered into page images. Amazon Textract processed the page images to extract text, entities, and table data. The extracted attachment text was combined with the email body text and sent to Anthropic Claude on Amazon Bedrock for classification into 13 service-request categories.

Sources & evidence1

Evidence: Low35/100Evidence strength