KPMG rebuilt how design and engineering work together, giving both sides a shared place to build on real code. Idea-to-production dropped from months to weeks.
88%
faster delivery
Months to weeks
for idea-to-production timelines
Same day
for design review cycles, from 10 days
Industry
Professional Services
About KPMG
KPMG is a global organization of independent services firms providing Audit, Tax and Advisory services.
Link copied to clipboard!
The component patterns indexed in Builder get us to roughly 80-90% accuracy, with a person validating the rest. Reviews that used to take ten days now happen the same day.
- Matthew Ardinger, Director of User Experience, KPMG
For most of his 25-year career designing for digital, Matthew Ardinger, Director of User Experience at KPMG, watched design and engineering run on the same rhythm. Designers pushed pixels, handed them to development, and waited. Engineers received those designs and rebuilt them from scratch. The entire path from idea to production took months.
The gap between intent and execution was the central problem. Designers created non-functional prototypes in Sketch and Figma, then handed them off. Weeks later, they would review the build, document where it had drifted from the original design, and start another round of redlines. The design and the shipped product lived in two different places, and keeping them aligned had become someone's full-time job.
Abhijeet Rokde, Specialist Director of AI & Digital Solutions and a front-end specialist with 15 years of experience, watched designs move from Figma to stakeholder review, then back through another round of updates. Weeks could pass before a single line of production code was written. When engineering finally received the designs, they rebuilt the HTML by hand, adding more time. Because the first build rarely matched the original intent, another cycle of reviews and fixes would begin.
KPMG's standards raised the bar further. The firm's reputation rests on how it handles client work, so security and privacy anchor every project. Plenty of AI coding tools could generate something quickly. Only a few could produce something that a consultancy of KPMG's standing could present to a client.
KPMG evaluated AI tooling across the market, and two things set Builder apart.
The first was the environment. Most coding tools gave Matthew a prompt and a little room to adjust around it. Builder felt like Figma, familiar enough that making the jump wasn't intimidating, and it let him go into the code once he was comfortable. He found himself manipulating CSS and JavaScript again, work he'd done years earlier and set aside when design tools took over.
The second was Builder's design intelligence system, which Abhijeet came to see as the firm's biggest differentiator. Builder connects to the codebase for context, then supplies the agent with explicit instructions: what a component is, when to use it, how it works alongside other components, how it connects to the back end, all backed by coded examples. The agent follows specific directions on what to use and how to use it.
With that in place, the design team built out a custom component library through a few steps:
New projects now draw on that library, and the team estimates output comes back close to fully aligned with KPMG branding and approved components from the start. Maintaining the design system used to fall to one dedicated person. Now the design team owns it directly, adding and revising components themselves, and the library carries through to every other coding tool they use.
The workflow changed for both sides. Designers push code through pull requests and branches, and engineers move into the design tab. Where designers once reviewed dev builds, compiled a laundry list of fixes with screenshots, and sent it back, they now make the change themselves from the same codebase, so the edit uses patterns the system already knows. The tight transitions and hover states that used to require sending a reference site now get built directly by the people who designed them.
Human judgment stayed central. Faster prototyping carries its own risk, the kind Matthew calls a "fever dream prototype," where anyone can build something and not all of it is good. Component patterns indexed in Builder achieve roughly 80-90% accuracy, with a person validating the remaining cases. Reviews that used to take ten days now happen the same day.
Behind those numbers, the bigger change is harder to quantify. Product, design, and engineering now work on the same surface, aware of each other's work and sharing joint ownership of what gets built. Design intent survives all the way through production, and over-the-wall handoffs have largely disappeared. When the design library changes, the design team flags it and engineering prompts the system to use the new version. For a firm where keeping product, design, and engineering aligned matters at KPMG's scale, that turned out to be the part worth building toward.
Designers have become developers, and developers are becoming designers.
- Abhijeet Rokde, Specialist Director of AI & Digital Solutions, KPMG
