Previously Outcomes (e.g., Approved, Denied, Manual Review) could not be deleted once they were created. Once an Outcome is deleted, it will be removed from the outcomes dropdown on the following pages:

• Evaluations
• Entity
• Workflow Editor
• Review Queue
• Review Reason when manually reviewing an entity

To delete an Outcome, go to Settings > Outcomes and click the trash can symbol next to the Outcome you would like to delete.

If an Entity had previously been assigned a deleted Outcome, nothing will change for that Entity. The deleted Outcome will still be reflected for that Entity.

Permissions will be set so that any agent that can create Outcomes can also delete them.

Admins can now set a permission to allow users to run What-If Analysis but not save changes. To set this permission, go to Setting > Roles.

To learn more about the What-If Analysis feature, view our documentation here.

2 new string comparisons now available: "Contains" and "Does not contain".

Prior to this we supported the following comparisons for strings:

• equals
• not equals
• regex match
• regex no match

"Contains" and "does not contain" are now available in this dropdown list. They are case insensitive.

The last name identifier field for sandbox personas is no longer case sensitive. This will make it easier to run sandbox personas whether or not the last name is capitalized.

You can now search for a workflow by name from your workflow list. Simply type the name of the workflow you are looking for in the search bar.

Alloy now allows you to make workflow decisions based on a proprietary dataset or model. For example, your company may have its own fraud model based on your own device and location data that you would like to apply in a workflow. Custom models were previously supported but now clients can set up these models much more quickly and independently.

We now allow clients to configure a “Custom Model” service within an Alloy workflow in the following way:

1. You host and configure an endpoint that Alloy will POST to during an evaluation with any service data that have been configured to run before the custom model
2. Your model returns a score to Alloy
3. You can configure decision thresholds based on that score in the Alloy dashboard

To learn more about how to use custom models, please reference our support documentation.

We have updated the Diligence panel to provide more contextual information on each of the fraud scores, making it easier to quickly assess the risk of each Entity. On the Diligence panel, third party fraud scores are now color-coded to reference each vendor’s best practice ranges. Green indicates low risk, orange is moderate risk and red is high risk.

When a user clicks the score, they will see more information about that specific fraud service and how they generate their score. This contextual information will give users clear insights to determine the next steps for each Entity.

The Manual Review modal for an Entity now displays the name of the Entity for contextual reference.