Back to Home

AI Product Design

I've worked on early AI concepts and shipped AI-enabled products. I bring practical AI product judgment: where AI adds real value, where it creates risk, and how to make it usable.

  • AI product fit: identify when AI meaningfully improves a workflow vs. when it feels forced
  • Trust and confidence: design for uncertainty, errors, confidence signals, and user control
  • Hands-on fluency: use AI daily for coding, design, video, avatars, writing, strategy, and prototyping. More about this in How I work

1. Conversational app creation

In 2020, long before ChatGPT or Cursor established the modern AI paradigm, I identified a major opportunity to transform UiPath Apps. The platform already offered a powerful low-code builder, but starting from a blank canvas created a steep adoption hurdle for business users, who often spent over 5 hours per app building initial prototypes.

To bridge this gap, I proposed complementing the manual builder with an AI-assisted creation path that let users bypass manual setup entirely by describing their app in plain English, uploading a PDF or image, or using a data entity to instantly generate a working starting point, reducing initial setup time by 85 percent.

After advocating for this vision with leadership and securing cross-functional alignment, I led the design team through the shift from canvas-first design to generative creation by architecting the end-to-end experience: prompt interfaces, document uploading, preview screens, and the critical editing transitions back into the visual canvas. The work required over 20 design iterations and laid the early groundwork for automated application building at UiPath. The concept eventually launched as a core feature of Autopilot in Apps, enabling non-technical users to create app scaffolding from natural text or image attachments while still relying on the existing drag-and-drop toolkit for precise adjustments.

Overall context

  1. UiPath acquired a low-code app built by a single developer in South Africa. The technology was strong, but usability feedback was negative. We began redesigning it. The drag-and-drop designer video below captures interactions I proposed—many of them shipped.

    Drag-and-drop app designer

  2. I proposed building an AI assistant into the app builder. The video below captures the essence of that proposal—and, about three years later, what the engineering prototype looked like.

    AI-driven app building: concept (2020) and working prototype (2023)

  3. I left UiPath before the full rollout, but the AI-assisted path later shipped as Autopilot in Apps, now part of the UiPath suite. You can read about it in the UiPath Apps documentation .

2. Smart copy/paste app (“Clipboard AI”)

Situation:

Enterprise users were still wasting time manually moving data from documents, receipts, IDs, and other sources into business systems.

Task:

As the design manager on the project, my role was to guide the product experience, make the AI capability easy to understand, and help communicate the product vision clearly.

Action:

I helped shape the core experience: extract structured data from a document, show what the system understood, and paste it into the right fields in the target workflow. I reviewed and directed design work, refined key mockups, clarified the flow, and helped make a complex AI interaction feel simple, useful, and trustworthy.

Result:

UiPath Clipboard AI was recognized by TIME as one of the Best Inventions of 2023 . As the design manager on the project, I oversaw the design direction, helped shape the experience, and refined key mockups and product storytelling assets. The project became a strong example of my ability to lead design for early AI products, translate technical capability into clear user experience, and communicate an emerging product idea in a way people immediately understand.

Other AI-assisted product experiences

  • UiPath Autopilot Concept 1

  • Document Understanding

  • UiPath Autopilot

  • Coaching App