Project NAFAS

NAFAS is a voice-first psychological safety companion for time-constrained triathletes and endurance athletes. The app pairs a non-judgmental AI companion, Kona, with daily check-ins, post-workout reflection, and lightweight insights to help athletes manage stress, build confidence, and maintain mental clarity alongside their existing training platforms.

The design challenge was not to replace coaching. Garmin and TrainingPeaks already handle performance data; NAFAS exists in the gap those tools don't touch, the psychological dimension of the training cycle. Every decision was tested against three questions: does this reduce cognitive load, does this respect athlete autonomy, and does this maintain psychological safety?

Endurance athletes, especially triathletes balancing training with work and life, have no dedicated digital space for the psychological side of their sport. The tools that exist are built for performance data, not mental state.

What Athletes Were Experiencing

• Anxiety, stress, and confidence loss mid-cycle with no low-friction outlet for reflection.
• Existing platforms (Garmin, TrainingPeaks) surface performance metrics but provide nothing for psychological support.
• No digital tools existed specifically for psychological safety in endurance training, athletes were managing this gap informally or not at all.

Design Goals

• Build a clear, low-friction onboarding experience that earns trust before asking for vulnerability.
• Deliver consistent, non-judgmental support through Kona without crossing into coaching or medical advice.
• Enable daily and post-workout check-ins that feel safe and lightweight, not like another task on the list.
• Provide minimal, reassurance-focused insights that reinforce confidence rather than highlight deficits.
• Respect athlete autonomy at every decision point: tone, frequency, and interaction style.

The research phase drew from three parallel sources: a competitive audit of endurance platforms, sports psychology literature on stress and burnout, and HCI research on voice-first, low-cognitive-load interfaces. The convergent finding shaped the entire design direction: the mental side of training is a relational problem, not a content problem.

Key Research Insights

• Athletes respond best to concise, empathic prompts, verbose or metrics-heavy responses increase anxiety rather than reduce it.
• Visual overload and excessive data are counterproductive in a psychological safety context: the experience needs to feel calm, not informative.
• Control over notifications, tone, and interaction frequency is a prerequisite for trust, athletes disengage when the app feels prescriptive.
• Existing platforms treat mental wellbeing as a content problem (articles, videos); NAFAS needed to treat it as a relational one, a companion, not a library.

Success Criteria

• Athletes complete onboarding without confusion, Kona's role as companion (not coach) is understood before the first real interaction.
• Check-in flows feel safe, supportive, and low-friction rather than clinical or interrogative.
• Users can locate insights, reminders, and chat within five seconds of landing on the home screen.

AI-Assisted Design Approach

This project used AI-assisted tools to accelerate ideation and test conversational tone. Lovable enabled rapid prototyping of onboarding flows and check-in screens. AI was used to generate layout alternatives, simulate emotional check-in scenarios, and test copy clarity at speed. All UX decisions, prioritisation, and strategy were led by me, AI was a collaborative tool, not a decision-maker.

Low-Fidelity Wireframes

Four wireframe screens were developed to validate the core interaction model before moving to high-fidelity design. Each screen addressed a distinct part of the experience: the home layout, the daily check-in flow, the Kona chat interface, and the insights screen.

The upgraded designs refined visual hierarchy, tightened the onboarding flow, and optimised the home layout for quick access to key actions. Every screen was evaluated against the same three questions that guided the project from the start: cognitive load, autonomy, and psychological safety.

• Voice-first check-in with text fallback, access to Kona is always one tap from the home screen.
• Progressive onboarding that earns trust before requesting vulnerability, Kona speaks first.
• Separate emotional and physical check-in scales preventing performance conflation.
• Text-only insights screen with weekly reassurance messages and a CTA to continue the conversation with Kona.
• Editable life/admin reminders with optional push notifications, maximum control, minimum overhead.
• Clear role boundary maintained at every interaction point: Kona is a companion, not a coach.

User testing is scheduled following the design review. Sessions will run with 6–10 endurance athletes unfamiliar with NAFAS, using remote moderated think-aloud protocols to validate onboarding clarity, chat usability, and perceived psychological safety.

Designing for psychological safety requires different constraints than designing for usability or conversion. The standard success metrics don't apply, success here is measured by whether the user feels safe enough to be honest, not whether they completed a funnel.

• AI honesty about its limits builds more trust than confident-sounding generic responses, athletes responded better to 'I'm not certain' than to plausible-but-wrong reassurance.
• Cognitive load is a psychological safety risk in this context, not just a usability inconvenience, every extra decision point is a potential exit for an already-stressed athlete.
• AI-assisted design accelerates iteration without replacing judgement: Lovable and AI-generated flows were useful for speed, but every decision about tone, constraint, and role boundary required a human call.
• Voice-first is a trust signal as much as a modality choice, it communicates that the experience is conversational rather than transactional.

NAFAS demonstrates that digital products can serve the psychological dimension of high-performance sport without crossing into coaching, therapy, or prescription. The design succeeds when it disappears, when Kona feels less like an app and more like a consistent, trustworthy presence that helps athletes hear themselves think.

The broader principle is that designing for psychological safety demands the same rigour as any complex UX challenge, but with different constraints. Clarity, honesty, low friction, and respect for autonomy aren't qualities to aim for in this context, they are the product.