Scaling account reviews by 20× by leveraging AI-powered decisioning.
Super.com is a consumer financial services platform that offers rewards and credits across travel and everyday purchases to millions of users.
Super.com relies on third-party risk scores and performance indicators to determine whether an account is eligible to receive credits. While these models perform well in aggregate, there are false positives — particularly for legitimate users whose behavior resembles automation.
Because these scores act as a hard gating mechanism, false positives have real consequences: legitimate users are delayed from receiving credits, user trust suffers, and Super.com's operations team is forced to intervene more often.
As Super.com grew, the volume of flagged accounts increased steadily — turning what were once rare exceptions into a recurring operational challenge. Super.com's risk team recognized that relying on third-party scores as the primary source for risk decisioning was no longer sufficient, and that additional context was necessary to maintain accuracy at scale.
The challenge wasn't that machine learning failed, but that opaque scores were asked to make nuanced decisions in isolation. The models lacked access to critical context, including:
Without this broader context, the system had limitations in consistently distinguishing malicious automation from legitimate activity.
To mitigate false positives, Super.com's risk operations team began manually reviewing flagged accounts. Analysts pulled together identity verification results, transaction histories, and behavioral signals from multiple internal systems, then weighed positive and negative indicators to determine whether credits should be released.
While this approach improved accuracy, it introduced significant operational friction. Each review required careful investigation and manual interpretation of multiple signals across systems, making the process slow and difficult to scale. What was originally intended as an exception-handling workflow quickly became a recurring bottleneck — delaying legitimate users and consuming increasing amounts of operational capacity.
Using Socratix, Super.com transformed its manual review process into an AI Operating Procedure — a human-defined, AI-executed decision workflow that evaluates identity, payment, and behavioral signals together. Rather than relying on rigid rules or a single model output, Socratix applies explainable, context-aware decisioning that mirrors expert judgment while remaining fully auditable and controllable.
The workflow was designed collaboratively by Super.com's risk team, ensuring it reflected their institutional knowledge and decision logic. Socratix executes that workflow at scale — consistently, transparently, and without requiring manual intervention for routine cases.
As a result, Super.com improved decision consistency, while maintaining the flexibility required for edge cases and removing manual review from the critical path — without sacrificing transparency or operational control.
Before Socratix, Super.com's team could manually review about 5 accounts per hour, with each decision requiring deep, cross-system investigation and subjective judgment.
Today, with Socratix:
What once required sustained manual intervention now runs automatically — allowing Super.com to scale account reviews by 20×, improve user trust, and operate with greater confidence and control, without sacrificing decision quality, transparency, or flexibility for edge cases.
See how Socratix AI can help your team make faster, more consistent decisions.