Setting new standards for financial confidence with AI

I led the design of the Financial Test Suite, a 0-to-1 product that continuously monitors a company's finances and flags anomalies before they become real problems. Its centrepiece is the Financial Test Agent: you describe what you want checked, like "find duplicate invoices," and it builds an editable test for you.

The impact

• Currently in Early Access, it's cut manual testing time by an average of 144 hours a month.

• Following its debut at Workday Rising, a record 61 customers, including Netflix and Salesforce, asked to join our design partner group to develop this product.

• Early feedback has been highly positive, with one customer calling it "an absolute game changer".

The problem

No enterprise company can manually verify that every transaction is correct, non duplicate, and free from fraud, but that's exactly how most finance teams operate. Checking happens reactively, at month end or audit time, by people manually comparing data spread across systems that don't talk to each other. By the time an error surfaces, the money has usually already moved.

Racing the clock

The project started as a few quick visuals for a leadership meeting on what automated financial monitoring could look like. Within days it became a 7-week sprint to launch at Workday Rising. With no time for the discovery or wireframing I'd normally do, I jumped on a call with my PM and designed content maps. I then fed those maps into Gemini to generate realistic data, which let me build believable, high fidelity screens fast. From there, I used Gemini as a synthetic research partner to test those screens, giving me enough signal to deliver a credible hero use case for the conference.

Defining AI interactions

One of the biggest questions we faced was where to introduce AI. Years of Workday research kept pointing to the same thing: implementation and setup are where products die, with customers getting buried in configuration long before they see any value. As a team we agreed that’s where AI could do the most good and focused our efforts. 

Rather than default to Workday’s existing chat interface, I designed a split screen canvas, a brand new pattern for Workday. The left side takes a plain-language request, like asking the system to scan for duplicate invoices. The right side shows the result in a structured, editable table, using the same components finance teams already use across Workday. The output isn't just familiar, it's something they can go in and adjust themselves.

Buying time to get it right

When senior stakeholders saw the first designs the feedback was consistent: good, but not enough AI, why not make the whole thing chat? My instinct was that reducing the product to chat would trade away the trust I'd just designed for, with little productivity gain, if any. With the conference deadline looming, I didn't have time to test that properly, so I held the core pattern and added a few smaller AI touches to answer the feedback without changing the structure underneath.

After the conference I had the room to test it properly. I prototyped a chat-first version of "View Details" and tested it against the tabular version with financial users. The reaction was immediate. One user put it bluntly: "Take me right to the data, I don't need the chatty, make me feel like I have a friend." View Details now opens straight into a filterable table with drill-down, with chat repositioned as a launcher and explainer rather than the destination.

Designing for trust

During user testing every participant described themselves, unprompted, as a "control freak". They needed to see the actual transaction, not be told about it, before they'd trust a flag. This shaped my interaction choices: every anomaly shows its source evidence, like the specific invoices involved, and the system never auto-corrects anything. Flagged items are put on hold, pending human review. That’s not to say we won’t have auto-remediation in the future, but at this point in time we are building trust in the system and its accuracy. As one customer described, they want the Agent to build credibility "like a co-worker".

The audit trail was as much a design decision as the drill down itself. For every flagged item, we show what decision was taken, who made it, when, and the context at the time. That record is what makes every action defensible to an auditor, not just to the user in the moment.

Learnings

Familiarity builds trust
Financial professionals think in grids and ledgers, not conversation. I anchored the AI experience in structured, editable artefacts that users were already familiar with. By respecting and building upon the user’s existing mental model I was able to quickly build trust and adoption.

Evidence over instinct
Years of working with these users gave me strong convictions, and when new leadership pushed back, my first instinct was to defend them outright. Instead, I bought time, held the line just enough to hit the deadline, and let user testing settle it once I actually had room to test.