Can Buy Lah

An AI-assisted product-understanding and price-comparison MVP for in-store shopping in Singapore.

Project background

01 / S / Project background

Chinese-speaking shoppers in Singapore switch among translation, search, marketplaces and social platforms before they can judge a product.

01English packaging
02Unfamiliar brands
03Fragmented price & reviews

Goal & role

02 / T / Goal & role

Independently take the product from user-problem mapping and AI output rules to error-case review and an accessible MVP.

01Problem mapping
02AI output rules
03Accessible MVP

What I did

03 / A / What I did

Rebuild the journey as capture → identify → search → understand → compare → decide, with three-tier matching for size, flavour and promotional-price edge cases.

01Capture → purchase decision
02Three-tier matching
03Price priority

Can Buy Lah discovery screen — 01 Capture product and shelf price in context.

Can Buy Lah product screen — 02 Organise product information, feedback and guidance.

Can Buy Lah price screen — 03 Compare in-store and online references for a clear decision.

Result & review

04 / R / Result & review

The MVP currently reaches 90%+ recognition accuracy and 85%+ effective price matches, with 30 invited test users and ongoing error-case iteration.

0190%+ recognition accuracy
0285%+ effective price matches
0330 invited test users

90%+image-recognition accuracy

85%+effective price-match success

30invited test users