Enterprise Knowledge Search
After launching more than 40 generative AI experiments, Sun Life needed to move from experimentation to production value with a secure way for employees to retrieve internal information quickly inside the company’s own technology environment.
Reported impact
Sun Life Asks is handling more than 10,000 employee queries each week, resolved more than 600,000 internal queries in its first 11 months, and saves team members hours of manual work so they can reinvest time in higher-value tasks while Sun Life prepares additional client-facing AI use cases.
Sun Life turned its early generative AI experiments into a production knowledge assistant by building Sun Life Asks on AWS. The chatbot runs inside the company’s secure technology environment and uses Amazon Bedrock to access Anthropic Claude models without Sun Life having to manage model infrastructure. Employee questions are grounded in internal company information, processed by Bedrock, and returned through the Sun Life Asks interface to staff across global operations. This architecture let Sun Life move from experimentation to value delivery quickly while keeping governance inside its own environment, and it created a reusable pattern for future client-facing use cases as the company scales broader generative AI adoption and workforce upskilling.
Employee questions and internal company information flow into Sun Life Asks, which uses Amazon Bedrock and Anthropic Claude to generate secure responses for employees across Sun Life’s global operations.
It easily saved me several hours of manual work.
Sun Life Asks resolved over 600,000 internal queries in its first 11 months.
Sun Life Asks uses Anthropic’s Claude through Amazon Bedrock.
Sun Life launched over 40 experiments, obtaining numerous lessons across its global operations.
employees are submitting over 10,000 queries a week.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
AWS Sample Nov 21, 2024 Discover Financial Services In its various lines of business, including decision and credit and portfolio risk management, Discover faced the challenge of making sure that it could launch its services fast enough. “We wanted to make decisions… The high compute power available was used for parallel model training, which reduced the processing time of 30… Amazon EC2 P3 Instances · Amazon EC2 P4 Instances · Amazon EFS AWS Sample Nov 7, 2024 BankUnited Cultivating service-oriented relationships is central to BankUnited's core mission. As such, the company wanted to help its employees more effectively surface information from its policy and procedures system, which… Key Outcomes accuracy rate 95% response times (less than 10 seconds) <10s support model established 24/7 Amazon Bedrock · Amazon Kendra · Claude 2 AWS Sample Sep 1, 2024 SBI Life Insurance SBI Life Insurance, an SBI Insurance Group company, provides consumers with products such as an affordable mortality insurance plan, which allows customers to revise the sum insured based on their stage of life; a… It also shortened the training periods by about 30 percent. Amazon Bedrock · Amazon Kendra · Amazon OpenSearch Service 