What challenges did SBI Life Insurance face before AI implementation?

Operators had to search across a large volume of product and procedural documents to answer questions about discontinued insurance products. Training new call-center operators was lengthy because they needed to understand many documents and policies. The company wanted quicker, more intuitive search that went beyond simple keyword matching.

What was the impact of the AI solution?

As of 2024, almost all operators were using the solution. The company reported about a 30% reduction in operator training time. The new search system improved responsiveness and reduced stress for call-center staff.

Source

Evidence: Medium50/100

SBI Life Insurance develops document search and selfbot support with Amazon Kendra and Amazon Bedrock

Use case typeLegal document summarizationUpdated Jun 13, 2026

SBI Life Insurance, part of the SBI Insurance Group in Japan, needed to reduce call-center operator workload and shorten training time for answering customer inquiries about discontinued insurance products and procedural documents. The company built an internal document search solution to retrieve product and policy documentation, and later added a selfbot that summarizes search results for faster customer support.

Organization: SBI Life Insurance
Industry: Insurance
Location: Japan
Published: May 2026

Reported outcomes

−30%

timeTime & speed

Strategic outcomes

Speed & agilityImproved responsiveness in call-center supportEmployee experienceReduced call-center staff stress

Catalog median for time & speed deployments: −50% across 312 reported metrics. Compare benchmarks →

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

Normalized claim

Time: 30% decrease

AWS Solutions Case StudiesMay 13, 2026Case studyInferred claimMedium evidence strength

The company reported about a 30% reduction in operator training time.

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

Customer: SBI Life Insurance
Provider: AWS
Maturity: Unknown
Linked source: AWS Solutions Case Studies

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 4

1Enterprise search
2Call center assistance
3Document summarization

Operators had to search across a large volume of product and procedural documents to answer questions about discontinued insurance products.
Training new call-center operators was lengthy because they needed to understand many documents and policies.
The company wanted quicker, more intuitive search that went beyond simple keyword matching.

SBI Life Insurance built the document search system around Amazon Kendra as the enterprise search service.
The solution indexes PDF brochures and procedural documents stored in Amazon Simple Storage Service (Amazon S3).
The team added a selfbot in 2023 that summarizes and displays Amazon Kendra search results using generative AI.
The article states that Anthropic's Claude is used through Amazon Bedrock to generate the summaries for operators.

Technologies

Amazon Kendra Amazon Simple Storage Service (Amazon S3)Amazon Bedrock Anthropic Claude

As of 2024, almost all operators were using the solution.
The company reported about a 30% reduction in operator training time.
The new search system improved responsiveness and reduced stress for call-center staff.

Architecture

Amazon Kendra is used as the core enterprise search service. PDF brochures and procedural documents are stored in Amazon S3 and indexed by Kendra. A selfbot layer summarizes Kendra search results using generative AI, with Anthropic Claude accessed via Amazon Bedrock.

Sources & evidence1

Evidence: Medium50/100Evidence strength