WorkFusion - AI Agent Tara (Payment Sanctions Screening Alert Review) - SaaS Single Tenant
Workfusion Inc. · Operations & Productivity
Certification per Microsoft Marketplace.
Evidence tier Source Confirmed · 9 captures on record
What the publisher says
As described on Microsoft Marketplace.
Tara, WorkFusion’s 100% digital Transaction Screening Analyst, is designed to protect your organization from sanctioned or risky client relationships by reviewing transaction alerts using different sanction lists. She is designed to ingest each alert generated by a financial institution’s sanctions screening system and determine if it is a false positive.
The AI Agent is agnostic to the screening system used and does not require tuning, sensitivity, or algorithm changes to the financial institution’s screening platform.
Show the rest of the publisher’s description (21 more lines)
WorkFusion does not replace Transaction Screening software but adds an extra layer to make the transaction and payment process more robust by automating Manual Tasks and reducing false-positive alerts.
Tara’s capabilities as Transaction Screening Analyst:
- Review and analyze alerted payment messages (e.g., SWIFT messages) to decide whether alert is valid or a false positive
- If the transaction is not determined to be a false positive, escalate to the analyst for further review
- Utilize and enrich information using approved sanction list(s)
- Continuously review alert messages (payment transaction messages) and hits to make decisions
- When needed, cross-reference message with third-party tools (e.g., Google, OpenCorporates.com) for more context and confidence in decision
- Provide written explanations for each decision
- Consult additional third-party sources to research organizations/individuals and support decision
- Handle exceptions with human-in-the-loop capability, working side-by-side with traditional team members.Integration:
WorkFusion offers out-of-the-box connectors that integrate with multiple types of screening systems such as
- Fircosoft
- OpenCorporates
- In-house Screening systems
- LexisNexisBenefits of end-to-end automation:
This AI-enabled, pre-trained AI Agent determines if a hit on a customer's transactions and pertained details (including originator and beneficiary details such as name, age, gender, and location) are a match or a false positive using a bank's internal KYC data and external data sources for confirmations (for example, connecting to government information portals, OFAC, UK, FATF sanction lists, and EU sanction lists) and determines if a customer’s details are relevant. Automating the transaction screening alert review helps drastically lower the number of false positives that traditional analysts review manually, thus reducing the time and manual effort required while increasing accuracy.
- Up to 70% + reduction in False positive alerts
- Provide standardized justifications for decisions
- Adaptive to ever-changing compliance and industry regulationsUsage based pricing
Usage for Tara's Payment Sanction Screening (PSS) skill is calculated and billed on a per transaction basis. For PSS, a single transaction is defined as an entity name (regardless of whether it is an individual, enterprise or vessel) that is submitted for investigation and successfully completes.
The submission of an entity name (i.e., Royal Mail Ship (RMS) Titanic) triggers an investigation. As part of each single investigation, Tara will search for mentions or “hits” of the entity on various sanction lists. Note that it is possible for zero “alerts” to be returned – this simply means that the entity is not mentioned on a sanctions list. Regardless of whether or not a “hit” or “alert” was found for the entity, a comprehensive audit in the form of a report is created as part of the output. Only investigations for entity names which did not complete (i.e., the investigation was cancelled or there was a system error) are excluded
Preview
1 imageAgent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-29
Plans and pricing as listed
5 listedSources
Publisher resources
4 linksLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.

