
September was about making self-serve smarter. SAR autofill picked up a much wider set of fields you can configure yourself, and Unit21 MCP got the tools it needs to actually filter and query your reports instead of just reading whatever a report already shows. On top of that, alert and case tables get new columns for entities and instruments, checklists support number and date fields, and Jack Henry Symitar customers can now push warnings straight back to their core. Here's what's new.
SAR autofill now covers a much wider set of fields than before: restricting inputs to FinCEN advisory codes, autofilling from entity data, mapping entity physical ID values to SAR form options, restricting TIN to the filing institution's TINs, autofilling account numbers from instrument data, and auto-checking items based on alert, case, entity, or instrument tags.
This is the first wave, focused on SAR fields, with more autofill coverage coming in future releases. A lot of what doesn't autofill automatically today is exactly what analysts fill in the same way every time. Now teams can map what they want autofilled once, and every filing after that pulls it in automatically instead of someone re-entering it by hand.
The Unit21 MCP server has two new tools this month: one to list a report's available filters, and one to list the valid values for each filter. Together, they complete the toolset for the report dashboard feature on the MCP server, so an AI assistant connected to Unit21 can build a valid report query without guessing at filter values.
Connecting an AI assistant to Unit21 only pays off if it can actually act on your data, not just read it. These tools let any MCP-connected assistant filter and query your reports directly, continuing the work we started when Unit21 MCP went live in August.
Alert and case tables can now show an Entities column and an Instruments column, each listing up to three associated records with a count for the rest. Turn it on per user through Choose Columns, or set it as an org default in Data Management > Display Settings. Investigators can see which entities and instruments are tied to an alert or case right from the table view, instead of opening each record to check.
The Prior Alerts, Prior Cases, and Prior SARs sections inside an investigation got the same upgrade: they now use the same tables as the main lists, so Choose Columns, sorting, page size, and column widths all work there too, following whatever column settings your org already configured. These sections used to be fixed tables with a hardcoded set of columns; now prior activity is just as customizable as the main alert, case, and SAR lists.
Checklists support number and date fields. Checklist items can now be number fields, with decimal precision, minimum, and maximum, or date fields, alongside the existing field types. Teams using checklists to standardize review steps can capture real structured data, like a dollar amount or a deadline, instead of working around it with a text field.
Automated Jack Henry Symitar warnings via PortX. Through our PortX partnership, Jack Henry Symitar customers can now automatically post warnings back to specific accounts in Symitar directly from Unit21, triggered by rule automation or manual action. Previously, marking an account as a warning meant manually switching into Symitar to do it; now that action can happen automatically, closing the loop between an alert in Unit21 and the warning showing up back in the core.
NACHA & X9 enrichment match visibility. A new view shows the results of NACHA and X9 enrichment matching: how many records were pending, matched, or had no match, plus the specific reason behind each match or non-match. Matching NACHA and X9 files to your core has always been difficult to troubleshoot; this view surfaces that directly, with the goal of reducing duplicate transactions between your core and your NACHA/X9 files.

Kunal Datta is the Chief Product Officer at Unit21. Prior to Unit21, he led the Product team for Checkout at Fast, and prior to that, led the Product teams responsible for automating aerial wildfire safety inspections at Pacific Gas & Electric.
He has a background leading Product teams using AI to automate processes at regulated entities, as well as financial products, machine learning products, web applications, mobile applications, hardware products, and data products. Kunal is a Fulbright Scholar and studied Civil and Environmental Engineering and Music Science Technology at Stanford University.