My Works
SneakySwing Coach Experience
The brief was AI verification. Coaches on the platform didn't need it. What they needed was something much simpler — and finding that changed everything built after.
Role
Product Designer
Period
Apr — May 2026 · 6 wks
Tools
Figma · Cursor
Impact
Roadmap redirected before dev started
The Problem
80% of coaches opened a task. None of them touched annotation.
THE BRIEF
Design an AI verification and lesson planning flow. Coaches would review the AI-generated diagnostic report, validate or override findings, prioritize issues, and build a training roadmap from those findings. The assumption: AI analysis was the core value-add that made the coach side worth using.
WHAT I FOUND
Drawing and recording exist on the same screen, but the annotation clip only captures a static frame with drawn lines and a voice note. The coaching process itself — scrubbing through frames, pausing at specific moments, the sequence of the analysis — doesn't make it to the student. What the student receives is a conclusion. Not a window into how the coach sees the swing.
Existing experience
The Diagnostics
Experienced coaches don't need AI to spot what's wrong with a swing. They can see it.
Interviews with coaches on the platform surfaced the same thing unprompted: they lead with the video, not the report. Every coaching session followed the same pattern — watch the swing, draw on the frame, record a voice note, send. AI analysis has real value for students and newer coaches. For experienced coaches already on the platform, it was overhead before the actual work could start.
The original brief had the order of operations wrong.
The AI had already flagged C-Posture. Coaches still led with what they saw.
The Decision
Ship the tool coaches already reach for. Reposition AI where it actually helps.
The to-be flow — student management, AI-assisted feedback, prescription and lesson planning — was the right long-term architecture. It wasn't the right first thing to build.
Coaches were already using third-party apps — V1, OnForm — that screen-record the annotation process. Scrubbing to the right frame, pausing, drawing in sequence: that's how coaches teach. SneakySwing's existing tool sent students a single annotated snapshot and a voice note. The coaching process didn't make it through.
Building with screen recording — so the clip captures what the coach actually does, not just where they ended up — was the one move that made the output useful.
AI didn't get removed. It got repositioned. Inside the annotation flow, AI generates a text summary of the coach's voice recording so coaches can review and edit before sending. That's AI at the right stage: assisting the coach's process, not replacing their judgment.
The co-founder/CTO made the final call. The direction came from what coaches said in research.
The Build
Six weeks. No PM. Research to roadmap redirect.
Every component ships with its own instructions. Developers don't need to ask. Designers don't need to guess.
01
Coach Research → The Pivot
Synthesized BD outreach notes and conducted direct interviews with coaches on the platform. The goal wasn't feature requests — it was understanding how coaches actually teach. What came back was consistent: every session was the same pattern. Watch the video. Draw on the frame. Record a voice note. Send. The AI diagnostic report was never part of it.
That insight redirected the roadmap.
02
Prototype + Testing → The Confirmation
Designed the to-be flow in Figma, built it as a Cursor prototype, and tested it with coaches. The workflow direction held up. What testing revealed was one specific problem: a single screen requiring too many decisions at once. That's a UI fix, not an architecture problem. One iteration, resolved.
The annotation flow — draw, record, AI summary, review, send — was designed to the full interaction level: loading states, confirmation dialogs, error cases. When AI can't generate a summary, coaches fill it in. The flow doesn't wait on AI.
The Impact
The most significant outcome is what didn't get built.
80%
Drop-off rate identified before any fix was coded
1 prototype
Led to one roadmap redirect, before dev started
0
PMs on the team — scope defined throughout
The original plan was to build an AI verification flow before validating whether coaches would use it. Building and testing a prototype first surfaced the answer before a single line of production code was written. Development starts the week of May 25, 2026 — pointed at the annotation feature coaches actually reach for, not the AI flow the brief assumed they needed.
Reflection
Sequencing is strategy.
The AI features aren't wrong. They're not the right starting point. Experienced coaches have years of diagnostic judgment — AI analysis is redundant for them at this stage. For students and newer coaches, it's exactly the right tool. This project is about getting the sequence right: give coaches what they already reach for, then layer in AI-assisted features as the relationship between coach and platform matures.
What I'd do differently: start research before design runs in parallel. This project had both happening simultaneously — I was designing the to-be flow while still gathering the insights that would refine it. The prototype ended up being essential, so no design work was wasted. A cleaner research-first phase would have tightened the loop.
