Demo for Nida Unas · Director of Loyalty, Digital & Marketing
Aura tracks the spend.
Wajha causes the spend.
AI-powered shopping discovery across H&M Kuwait, Foot Locker, Mothercare, and Bath & Body Works — 673 real SKUs, real Adobe AEM imagery, real prices.
Toggle Stage 1 · Pilotfor what we're proposing to ship, or Stage 2 · Preview for where the product goes once traction proves out (unified cart + Aura Concierge checkout).
1→
English text search
“white t-shirt under 8 KWD” — cross-brand AI search across the Alshaya catalogue, in English
2→
Arabic text search
“فستان” (dress) — multilingual embeddings, no translation layer, Arabic queries handled natively
3→
Visual similarity
Tap a product → find visually similar across H&M / Foot Locker / Mothercare / BBW
4→
Complete the look
Pick an outfit → AI bundles matching items across all the OTHER Alshaya brands
5→
Price ladder
“love this but it’s outside my budget” — find visually similar at discounted price
What this demo is — and is not
- ✓ Real catalog data scraped from Alshaya-operated KW storefronts (Adobe AEM Edge)
- ✓ Real CLIP (512-dim) image embeddings, real Cohere multilingual (1024-dim) text embeddings in Supabase pgvector
- ✓ Real cross-brand kNN search via Postgres HNSW indexes
- ✓ Stage 2 cart + Concierge checkout walkthrough (mocked — no payment, no real orders)
- ! Checkout writes nothing to brand sites; success page is illustrative
- ! Stage 1 is the pilot ask; Stages 2 and 3 are visible here for context only