customer_support · logistics · workflow
DTDC builds DIVA 2.0 with Amazon Bedrock, reducing customer support queries by 51.4%
DTDC's existing logistics agent DIVA handled over 400,000 monthly queries through a rigid, guided workflow that forced users along a structured path, leading to longer resolution times, greater burden on human support agents, and poor customer experience.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits natural language query
An end-user accesses the logistics agent through the DTDC website and submits queries in natural language.
Tools used
Amazon BedrockAmazon Bedrock AgentsAmazon Bedrock Knowledge BasesAmazon Bedrock GuardrailsAWS App RunnerAWS LambdaAmazon CloudFrontAmazon S3Amazon OpenSearch ServiceAmazon RDSAmazon CloudWatch LogsAWS CloudTrailAmazon GuardDutyAmazon API GatewayAWS Identity and Access ManagementClaude 3.0
Outcome
DIVA 2.0 achieved 93% response accuracy and reduced the volume of queries handled by the customer support team by 51.4%, with 51.4% of consignment inquiries resolved without requiring a support ticket.
What failed first
The original DIVA system used a rigid, guided workflow that lacked flexibility and could not handle dynamic conversations, creating poor customer experience and increased reliance on human agents.
Results
Time savedover 400,000
Volume93%
Grounding & classification
Source type: technical build writeup
47 fields verified against source quotes.
agentic workflowai agentconversational aiknowledge searchragknowledge basesupport ticketmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedlogisticsaccuracy improvementcustomer satisfactiondeflection rateresolution time reductiontechnical build writeupcustomer supportlogistics opsticket triageautonomous resolutionescalation workflowrag answering