Master vendor data is critical for enterprise finance teams—poor data leads to fraud risk, duplicate payments, and costly errors. I redesigned the duplicate vendor review experience to help AP teams work faster with greater confidence.
See duplicate flag
in Xelix
Click Acknowledge
No details visible
Leave to ERP
Context lost
Compare in SAP
Copy/paste IDs
Return to Xelix
Re-find record
Acknowledge
No feedback
Fragmented workflow with platform switching
[001] THE OPPORTUNITY
Our platform identified duplicate vendors, but reviewing them was slow and disconnected. AP teams spent 3–4 hours each day switching between Xelix and their ERP to validate matches. At the same time, a new ML model presented an opportunity to reduce false positives and learn continuously from user decisions, but only if the review experience was redesigned.
[002] RESEARCH
Interviews with finance teams at Currys (£10B revenue), DS Smith (£7B revenue) and Liberty Global ($7B revenue) showed users trusted bank account and tax ID matches far more than vendor names. Rather than another confidence score, they wanted clear evidence that helped them validate decisions without leaving Xelix.
"Having a lot of vendors open makes for a messier ledger. When you've got a massive master data file, you're not getting the benefits of scale. What you want is to have one good deal with one supplier." — Katie, Senior AP Manager
[003] EXPLORATION
I facilitated a cross-functional design studio with Product, Engineering and AI to explore multiple approaches including drawers, comparison matrices and recommendation-led workflows. Customer testing showed the comparison workspace dramatically reduced effort, but also revealed a concern: replacing the familiar AG Grid interface too abruptly would create cognitive overload. We instead embedded the comparison workspace within the existing workflow, making adoption feel incremental while creating a reusable interaction pattern for future AI-powered review experiences.
01
Engineering constraints
02
Concepts rejected
03
Turning point
[004] SOLUTION
The final experience centred around a dedicated comparison workspace launched from the familiar review table. Users could compare vendors side by side, highlight matching evidence, pin a primary record, classify duplicates and train the ML model through Yes/No/Ignore decisions, all without leaving Xelix.
"We spend about 70% less time… everything we need is right there… what used to feel like a chore now feels manageable." — Jeff, Senior AP Manager, Energy Transfer
[005] IMPACT
Energy Transfer identified 20% duplicate vendor records, uncovering $1.7M in duplicate payments and recovering $540K within 60 days. Review time fell from 3–4 hours to under 45 minutes. Customer feedback also confirmed the redesign made duplicate review substantially easier, while every Yes/No/Ignore decision now improves future ML detection.