Customer Service Automation · Enterprise Knowledge Search
DoorDash needed to handle hundreds of thousands of support calls with faster, lower-latency self-service for Dashers while keeping answers grounded, safe, and accurate.
Reported impact
DoorDash reported increase in testing capacity 50x, response latency with Anthropic's Claude 3 Haiku, and 2.5 seconds or less, improving generative AI contact center self-service with measurable gains in productivity improvement, customer experience, speed to market, and scalability.
DoorDash uses Amazon Connect Customer, Amazon Lex, Amazon Bedrock, and Anthropic's Claude 3 Haiku in Amazon Bedrock to support generative AI contact center self-service. DoorDash needed to handle hundreds of thousands of support calls with faster, lower-latency self-service for Dashers while keeping answers grounded, safe, and accurate. In practice, the implementation runs transformation or AI logic on Amazon Bedrock, and delivers outputs through Amazon Connect Customer. Tickets, conversation history, knowledge articles, and operational context are consolidated into a governed cloud data layer; Amazon Bedrock applies analytics or model logic; results are surfaced through Amazon Connect Customer. The case study reports increase in testing capacity 50x, response latency with Anthropic's Claude 3 Haiku, and 2.5 seconds or less, showing measurable improvement after the rollout.
Tickets, conversation history, knowledge articles, and operational context are consolidated into a governed cloud data layer; Amazon Bedrock applies analytics or model logic; results are surfaced through Amazon Connect Customer.
2.5 seconds or less
increase in testing capacity 50x
of calls per day fielded by generative AI solution 100Ks
reduction in generative AI application development time using Amazon Bedrock 50%
response latency with Anthropic's Claude 3 Haiku
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
In-house Sample Est. · Jul 16, 2026 Poste Italiane Poste Italiane needed to use its large, distributed data estate and national omnichannel service network more effectively so employees could respond faster during customer interactions, customers could access services… 25 million daily customer interactions AI-supported telephone booking service · Cloud and Edge Computing · Poste Italiane single app 
AWS Sample Sep 11, 2024 Georgia-Pacific The lack of a centralized, readily accessible knowledge base often leads to reduced machine productivity, prolonged machine downtime, and higher troubleshooting and repair costs. Making phone calls to experts and… Accelerated operator onboarding Amazon Bedrock · Amazon Kinesis 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 