compliance_monitoring · ecommerce · workflow
How Amazon uses AI agents to support compliance screening of billions of transactions per day
Amazon must screen billions of transactions daily across its global businesses for sanctions compliance, but the human-intensive review approach creates significant bottlenecks—manual review cycles can take days, directly impacting customer experience through delayed transactions, account holds, and order fulfillment disruptions.
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 · Transactions enter screening pipeline
Amazon screens approximately 2 billion transactions daily across 160+ businesses globally to prevent prohibited transactions.
Tools used
Amazon SageMakerAmazon BedrockAmazon Bedrock AgentCore RuntimeStrandsThinkTool
Outcome
The AI-powered investigation system achieves 96% overall accuracy with 96% precision and 100% recall, automates decision-making for over 60% of case volume, and screens approximately 2 billion transactions daily, outperforming humans on historical decisions.
Results
Volumeapproximately 2 billion
Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes, 1 dropped as unverifiable.
agentic workflowdata extractionmulti agent workflowsummarizationid documentknowledge basefailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedworkflow describedecommercesoftwareaccuracy improvementautomation ratethroughput increasetechnical build writeupcompliance monitoringkyc amlagentic task executionautonomous resolutionescalation workflowextract classify route