tap ASK to load
Side project · live·9 min read·AWS Hackathon
STYLEMAX
A fashion companion that turns closet chaos into curated confidence, using the items you already own.
morning decision timetap to collapse →
15min→<30sec
Try this · ask Stylemax
Pick a mood. Pick the weather. Watch three agents argue — and out comes an outfit from a closet you already own.
mood
weather
idle
idle
idle
3 outfits · from your closet
waiting
tap ASK to load
tap ASK to load
TL;DR
01. TL;DR
🧥 Problem: 65% of professionals lose 10–15 minutes every morning deciding what to wear, while ~80% of their wardrobe sits unworn.
🤖 Strategy: Instead of one black-box AI that decides everything, split the job across three smaller AIs. One reads the closet. One styles outfits. One spots ignored items. Each can be checked and explained on its own.
⏱ Impact: 10–15 min decision collapsed to under 30 seconds. ~2.5× more outfit combinations from the existing wardrobe.
Problem
02. Problem
Closet paralysis isn't a "more recommendations" problem.
It's a seeing what you already own problem. Most new AI fashion tools were built to push users toward buying more, not wearing what they already own. The opportunity was to prove AI that gives control back to the user. One that earns trust instead of selling them their next purchase.
Bringing items back into rotation, surfacing the neglected and weather-matching the forgotten. This moves wardrobe utilization from 20% to roughly 50%+. The wardrobe didn't change but the awareness did.
How I Decided the Path
03. How I Decided the Path
The choices behind the product — what I picked and what I deliberately said no to.
Each agent tested in isolation against a sample wardrobe before being wired into the cross-agent loop. Kill criteria for hallucinated items were defined before the stylist prompt was written.
rejected · single model
- opaque failure modes
- no place to insert guardrails
- can't explain why to the user
rejected · shopping recs
- a tool meant to reduce buying pressure
- can't quietly sell things on the side
selected · three agents
📷👕👍
- each agent: own prompt + temperature
- guardrails at the seams
- suggestions with reasoning
The three agents · interactive detail
Three agents, three prompts.
Intake
temp 0.2 · accurate categorization
Tag the closet.
Reads photos + user notes. Returns clean item tags: type, color, season, formality.
// prompt
You are a careful clothing cataloger.
Given a photo and optional user note,
return JSON:
{ id, type, color, fabric,
season, formality }
Refuse to guess. Output null
for anything unclear.Stylist
temp 0.7 · creative combinations
Compose three outfits.
Returns item IDs only — never names. Unknown IDs are silently dropped before the user sees anything.
// prompt
Given mood + weather + closet,
return 3 outfits as item IDs:
[[id, id, id], …]
Never invent IDs. If < 2 valid
items in an outfit, discard it.
One-line reason per outfit.Behavioral
temp 0.7 · neglected-item radar
Surface what's forgotten.
Flags items unworn for 3+ weeks. Wear history closes the loop — once worn, the flag clears.
// prompt
For each item, compute days
since last_worn. If > 21, mark
as candidate. Boost into next
stylist context. User's explicit
"will try" outranks AI flags.
Intent > inference.How I Built
04. How I Built
Three agents, three temperatures. Intake 0.2 (accuracy). Stylist + Behavioral 0.7 (creativity). Each agent tunable, testable, explainable without corrupting the others.
What the user picks always beats what the AI guesses. Items the user explicitly tapped "Will try" outrank items the behavioral agent flagged. User preference over AI suggestion.
No shopping recommendations. No body-type prescriptions. Encoded as launch criteria in product scope.
Cross-Agent Feedback Loop
05. Cross-Agent Feedback Loop
The user's own behavior closes the loop. The AI gets out of the way the moment the user wears the unworn item. (problem solved!)
Hover or focus each box — the connecting flow pulses in that direction.
Impact Delivered
06. Impact Delivered
What it moved.
<0sec
Morning outfit decision timefrom 10–15 min of closet paralysis
~0.0×
more outfit combinations from the existing wardrobe
neglected items injected back into rotation
3–0sec
AI response time per request
three weather-aware, mood-matched outfits · one-line explanations
Why This Matters
07. Why This Matters
Responsible AI isn't a separate workstream from product velocity. Splitting the system into three named agents, with three named temperatures, gave me three named places to put guardrails, and three named things to show the user. The seams are the explanation.
⠀
Live prototype
Try Stylemax yourself.
Live at stylemax.amplifyapp.com ↗ — embedded below.