Building Trust in AI Design

ditto is an AI-powered marketing assistant for small businesses and agencies. As the sole UX designer and co-founder, I was responsible for shaping how users experienced the product's core value: let the AI handle your marketing content, and trust that it'll sound like you.

That second part, trust, turned out to be the central design problem.

The Challenge

AI-generated content is only useful if people actually use it. For enterprise users or marketing professionals, that bar is relatively low, they're comfortable editing and iterating. For small business owners, it's a different proposition entirely. Their brand voice is personal. A post that sounds slightly off feels like a misrepresentation of who they are.

The challenge was designing an experience that made users feel confident enough to let ditto's AI do its thing.

Research & Discovery

I conducted interviews with five participants: three marketing professionals and two small business owners. The differences between these groups turned out to be more significant than expected.

Marketing Professionals were comfortable with AI-generated drafts as a starting point. They evaluated output critically and edited freely.

Small Business Owners were emotionally invested in their brand voice. They were sceptical that AI could capture their nuance, and needed reassurance before they'd engage.

The small business owners weren't opposed to AI, they were protective of their brand. They wanted to see ditto demonstrate competence before handing anything over to it. That finding shaped the entire design direction.

Design Approach

Brand analysis as the trust foundation

An early product decision was having ditto analyse each user's existing marketing materials to learn their brand voice. It became a cornerstone of the UX strategy. Rather than treating this as a background process, I made it a visible, deliberate moment: ditto was learning about you, specifically, before producing anything.

The first usability test confirmed this was the right call. When our beta user saw ditto's first output, content that actually sounded like their business, her reaction was immediate. She hadn't expected it to be that accurate. That moment of recognition was the product's most powerful feature, and the rest of the design was built around earning it as early as possible.

Her reaction to ditto's first output was palpable. As soon as we finished the user test, we were both ecstatic. That single moment validated the core product thesis better than any metric could.

Control without friction

Usability testing surfaced a second challenge. Users were impressed by the output, but needed to make small, practical edits, specific products, current promotions, details that the AI couldn't know. I designed a context preview panel with three pathways: edit directly, regenerate entirely, or publish as-is.

The regenerate button was added in response to observed behaviour in testing. Some users found editing to be more effort than starting fresh, and a single click to regenerate gave them a faster route to something they were happy with.

Progressive onboarding

The onboarding flow was structured around getting users to their first piece of usable content as quickly as possible. Account connections and configuration were deferred until after that moment, so the first impression was ditto's capability, rather than its setup requirements.

Results

Key Learnings

Trust in AI is built through demonstration, not explanation. No amount of reassuring copy would have done what that first accurate output did. Getting users to a credible result fast matters more than any onboarding messaging.

The research also showed that emotional and practical trust operate differently. Marketing professionals were comfortable jumping straight to editing. Small business owners needed to see ditto get their brand right before they'd trust the output, so the onboarding led with the brand analysis result, letting ditto prove itself before asking them to do anything.