Overview
Coachscribe is an AI-powered sports coaching platform that turns performance data from training and match sessions into actionable insights.
I was hired as the first Product Designer on the project for a two-month engagement to understand why coaches struggled to interpret and act on the product’s insights. The product had significant potential but lacked clarity around what the data meant, what coaches should do with it, and how it fitted into their workflows.
My goal for this missing was to recenter the experience around coaches’ needs and how technology could best support their coaching.
Combining UX research, product strategy, information architecture and product design to create a simpler, more actionable experience.
The Challenge
Coachscribe had ambitious technology behind it, but the experience was becoming increasingly complex. The product exposed coaches to large amounts of data and AI-generated analysis, but more information wasn't necessarily helping them make better decisions.
I needed to understand:
What information do coaches actually need and when?
Which insights are genuinely actionable?
How much complexity can they reasonably absorb?
How could the product work across different sports, teams and coaching contexts?
The goal became to move from an AI-first product towards a coach-first product.
Screenshot of the original dashboard landing page.
Starting with the people, not the interface
I started by working with the team to understand the business needs behind the product, then proposed to conduct a discovery research across different roles and sporting contexts, speaking with 8 coaches and performance/data professionals from organisations including Yale Men's Golf, Stanford Women's Volleyball and the New York Giants.
I need to understand:
what information they trusted?
what they were trying to achieve?
which insights helped them make decisions?
This exposed a key tension in the product: coaches didn't necessarily need more analysis. They needed the right analysis, presented at the right moment, with enough context to understand what to do next.
Screenshot of the research exercise exploring which AI-generated session statistics coaches considered most valuable, and the context behind how they use those insights to inform their decisions.
Aggregated research insights, organised by team.
Four principles for a clearer product
The research led me to establish four principles to guide the product experience:
1 - Clarity: reduce cognitive load and make the most important information immediately understandable.
2 - Explainability: When AI makes a recommendation or surfaces an insight, coaches need to understand why.
3 - Guidance: Move beyond presenting information towards helping coaches understand what they could do next.
4 - Team identity: The product should reflect the way a team actually works and thinks.
These principles became a framework for evaluating both existing features and future product ideas.
From dashboards to decisions
The research also pointed to a clear direction: move from presenting data to supporting decisions.
Reduce visible data by ~30%: prioritising the insights most relevant to the coach’s immediate task.
Structure the experience around coaching moments: rather than datasets and metrics.
Introduce concepts like Game/Event Gap: surfacing meaningful differences between events and turning data into actionable coaching conversations.
Absorb complexity behind the scenes: letting the technology handle the analysis while presenting coaches with clear, actionable insights.
To illustrate the proposed direction, I designed a new web UI translating the research insights into concrete recommendations for the future product which I presented to the team.
Early wireframe exploring the proposed dashboard structure and UI.
Proposed dashboard redesign, translating research insights into a clearer coaching experience.
Due to budget constraints, the engagement ended before I could take the proposed direction further into design and implementation.
Outcome
My work helped shift the conversation from "What can our AI do?" towards "What does a coach actually need?"
The result was a clearer product direction centred around:
reducing unnecessary complexity
prioritising actionable insights
making AI recommendations more understandable
designing around real coaching workflows
giving mobile and web distinct roles
creating a stronger foundation for future product development