Evidence: Low35/100

dLocal automated compliance reviews with Amazon Quick Automate

dLocal automated merchant compliance website reviews to scale onboarding and ongoing reevaluation of merchant websites. The solution navigates merchant sites, extracts product information, checks against prohibited categories, classifies results, and routes ambiguous cases to human review.

Organization
dLocal
Industry
Finance
Location
UY
Published
December 2025
Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Merchant website reviews fully automated: 75% increase

AWS Machine Learning BlogDec 23, 2025Blog postExplicit claimLow evidence strength

“With Quick Automate, dLocal achieved a breakthrough in compliance automation, with up to 75% of merchant website reviews completed fully automatically”

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
Customer
dLocal
Provider
AWS
Maturity
Unknown

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 2 of 2

  • 1Workflow automation
  • 2AI agents
  • Implemented a multi-agent automation with UI automation, API integrations, and orchestration using Amazon Quick Automate.
  • Configured a UI Agent to navigate websites, extract data, reason against more than 15 prohibited categories, and generate structured evidence for compliance decisions.
  • Saved compliance results in Amazon S3 and routed ambiguous cases to human review.
  • Up to 75% of merchant website reviews were completed fully automatically in controlled evaluations.
  • Compliance specialists shifted from routine checks to complex cases, and the company gained continuous monitoring across its merchant portfolio.
Architecture

The solution uses Amazon Quick Automate with a UI Agent to navigate merchant websites, extract product information, evaluate offerings against policy categories, classify cases as Approved, Rejected, or Website Inaccessible, and route ambiguous cases to human-in-the-loop review. Compliance results are stored in Amazon S3, and case management supports parallel processing and logging.

Sources & evidence1
Evidence: Low35/100Evidence strength
  • Customer explicitly identified
  • Quantified outcome available
  • Technical implementation details available
Type: Blog PostPublished: Dec 23, 2025Publisher: AWSEvidence: VendorConfidence: Medium

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Community

Comments

No published comments yet.