Snowflake and Amazon Quick Cut AML Verification from One Hour to Five Minutes

Amazon and Snowflake joined forces to accelerate one of the most labor-intensive processes in fintech — checking suspicious transactions to detect money laundering (AML). The result exceeded expectations: analysis time has been reduced from one and a half hours to less than five minutes.

Why this was a problem

Banks and financial companies receive thousands of alerts daily about potentially suspicious transactions. Each alert must be checked manually — an analyst reviews payment history, customer data, geography, spending patterns. This takes from half an hour to one and a half hours per case. The process is expensive, slow, and prone to human error. Compliance teams in large banks sometimes queue up waiting for verification. Transactions get delayed, customers complain, costs rise. Most importantly, it's impossible to check all alerts with equal thoroughness. Priorities have to be set, which means something can slip through.

How Amazon Quick + Snowflake Cortex works

Amazon Quick Flows and Snowflake Cortex AI connect through Model Context Protocol (MCP). The workflow automatically collects information about the customer and transaction, passes it to AI, and receives a recommendation about the alert status. The analyst only needs to confirm or reject the machine's decision. The process looks like this: the system takes data from payment systems, customer history, their KYC (Know Your Customer) profile, and transaction geography. Snowflake Cortex analyzes all of this in context and provides a risk assessment — high, medium, low. If necessary, the system suggests additional steps or, if the risk is clearly low, closes the alert automatically.

What the system does

• Collection of data from various sources (payment systems, transaction history, KYC databases)
• Analysis of customer behavior through Snowflake Cortex AI
• Automatic risk ranking with explanation
• Report preparation for the analyst
• Logging for compliance and audit

All of this happens in seconds instead of one to one and a half hours.

Numbers from testing

Amazon and Snowflake conducted testing and obtained these results:

• Alert verification time: from 30–90 minutes to less than 5 minutes
• Analyst workload: reduced by 80–90%
• Throughput: one team can process 10 times more alerts
• Accuracy: AI catches patterns that people miss

Results depend on alert complexity, data volume, and workflow configuration, but even in the worst scenario, the gains are significant.

What this means for financial services

Financial organizations get a tool to detect fraud and money laundering faster, while freeing people from routine work. This is especially important when volumes are growing and finding compliance specialists is difficult. For AWS and Snowflake, this is another example of how AI can make a real difference in enterprise processes and MCP becomes the standard for integrating different systems.