Giving Frankie a character
Designing the personality, voice, and behavioral system for Fringe’s AI experience
Fringe explored how conversational AI could help HR practitioners move from question to action faster. An internal sprint produced the first version of Frankie: a conversational interface that could answer questions, surface information, and guide people through tasks.
The prototype proved the idea had potential. But putting it into the product exposed a different design problem.
If conversation was going to become part of the interface, who was the user actually talking to?
My work evolved from bringing the prototype into the Fringe product experience to defining the character, personality, voice, and behavioral principles that could make Frankie feel coherent across conversations—and give the team a shared system for designing what came next.
Role
Senior Product Designer
Senior Product Designer
What I owned
Experience design · UI design · Character strategy · Research · Personality · Voice & tone · Conversation principles · Workshop facilitation
Experience design · UI design · Character strategy · Research · Personality · Voice & tone · Conversation principles · Workshop facilitation
From prototype to product
Frankie began as a prototype that Swain Strickland built during an internal sprint. The concept won the sprint and gave the team something tangible to build on: a conversational way for HR practitioners to interact with Fringe.
My first role was bringing that experience into the product itself, aligning the interface with the Practitioner Dashboard and the broader Fringe experience.
That work made the next problem much easier to see.
A chatbot can look like the rest of the product without behaving like it.
As we used Frankie in more realistic situations, inconsistencies emerged in how it responded, how much it said, when it offered help, and what kind of relationship it seemed to have with the person on the other side of the conversation.
We didn’t just need better responses.
We needed a character system.
Designing the person behind the interface
I started treating Frankie as two related design problems.
Character covered identity, psychology, personality, voice, behavioral principles, conversational modes, constraints, and examples of how Frankie should respond.
Visual identity covered how that character might appear in the product: avatar direction, expression, presence, states, and eventually motion.
The character needed to come first. A face without a coherent personality would only make inconsistent behavior more noticeable.
I researched voice-and-tone characteristics and developed ways to make subjective personality questions more concrete. Instead of asking stakeholders whether Frankie should simply be “friendly” or “professional,” I wanted us to decide how Frankie should actually behave.
Building alignment around a character
On May 14, I facilitated a character workshop with product and executive stakeholders.
The goal wasn’t to pick adjectives. It was to establish a shared mental model for how Frankie should relate to people.
We explored questions around authority, warmth, initiative, humor, expertise, brevity, and support behavior. The discussion helped reveal an important tension in the character.
Frankie needed to be both a coach and a concierge.
As a coach, Frankie could help practitioners understand what mattered, make sense of information, and move toward a decision.
As a concierge, Frankie could reduce effort—finding things, surfacing the right information, and helping people get something done.
Those modes gave us something much more useful than a list of personality traits. They gave the team a framework for deciding how Frankie should behave in context.
Conversation is the interface. Action is the point.
That distinction became central to the work.
Frankie wasn’t intended to become another search bar, help center, or support bot that simply routed people elsewhere. The opportunity was to reduce the distance between people and the things they were trying to do.
At the time, that meant helping HR practitioners answer questions, surface relevant data, and navigate tasks within the ADP Connect experience. Longer term, the same interaction model could support more direct action and additional audiences.
The conversation itself wasn’t the destination.
The work getting done was the point.
That changed how I thought about the character. Frankie shouldn’t maximize conversation. It should know when to explain, when to recommend, when to act, when to hand off, and when to get out of the way.
Turning personality into product behavior
The workshop and research became a working system for personality, voice, and tone.
I translated the character into practical guidance for things like:
• how direct or conversational Frankie should be
• when to lead versus when to follow
• how much context to provide
• how to handle uncertainty
• how to recover when a conversation wasn’t working
• how calls to action should enter a conversation
• how the Coach and Concierge modes should affect a response
• what Frankie should avoid doing
The aim was not to outline every exchange. Instead, it was to set system limits robust enough to ensure consistency while preserving flexibility.
That also meant recognizing failure patterns. During iteration, the team encountered behaviors such as repeated responses, missed or dropped calls to action, unanswered questions, stalled conversations, and loops where Frankie failed to pivot when a user wasn’t getting what they needed.
Those failures helped make the behavioral guidance more concrete.
Documentation became part of the product
I documented the personality, behavioral principles, and voice-and-tone guidance in Markdown.
That format mattered.
The documentation wasn’t only a reference for designers and product partners. It could become operational input for the AI itself.
Tho Le used that modular guidance while developing the next iteration of Frankie. Instead of translating a brand personality from a presentation into ad hoc prompts, the implementation could draw from explicit instructions on how Frankie should communicate and behave.
Other team members also continued refining specific interaction behaviors, including literal-answer and handoff cases.
The character system had moved from design guidance to product infrastructure.
Designing a face for Frankie
In parallel, I explored how the character might become visible.
That included naming and avatar directions, expressions, states, sizes, and ways Frankie might appear across different product surfaces. The challenge was to create something recognizable enough to feel like a character without making the experience childish, overly anthropomorphic, or disconnected from Fringe.
But this part of the work deliberately remains unfinished.
Product priorities shifted toward experiments and discovery before we settled on a final name or avatar direction. Rather than retroactively presenting one exploration as “the answer,” I think the unresolved work is useful evidence of where the project actually stopped.
The behavioral system had become actionable. The visual character had not yet reached the same point.
What Frankie taught me
Designing an AI-enabled experience changed the boundary of what I considered interface design.
The UI mattered. So did the words. But neither was sufficient on its own.
For a conversational product, personality becomes interaction design. Traits like confidence, restraint, initiative, warmth, and brevity affect what the system does—not merely how its copy sounds.
And once those decisions can influence model behavior directly, design documentation takes on a different role. It isn’t only explaining the product after decisions have been made.
It can become part of the system that produces the experience.
Frankie never reached a final visual form while I was at Fringe. But the work established something more fundamental: a shared model for who Frankie was, how Frankie should behave, and how to translate that character from design intent into an AI-enabled product.
