Yash Khoury — Index 2026
pearl
000
Yash KhouryApplied AI builder ·
Exhibit 04 — Procurement / product intelligence← All work


A marketplace-agnostic sourcing engine for query planning, offer normalisation, deduplication and evidence-based supplier/product ranking.

Stack
TypeScript
Year
2026
Last updated
Source ↗
AI Product Sourcing Agent: iridescent glass study

Why it exists

Cross-marketplace sourcing creates a comparison problem: listings use different currencies, units, terminology, supplier evidence and duplicated offers, so search volume alone does not produce a procurement decision.

How it’s built

The AI Product Sourcing Agent is a procurement intelligence layer that compares marketplace offers on consistent evidence instead of treating search results as interchangeable products.

  1. Plan multiple search queries instead of betting the sourcing result on one wording.
  2. Normalise offers into a shared product/supplier model.
  3. Deduplicate repeated or near-identical listings before ranking.
  4. Rank with observed evidence and preserve provenance for the operator.

Capabilities

Query planningMarketplace abstractionOffer normalisationCross-market deduplicationEvidence-based rankingSupplier/product provenance

Principles

Evidence before enthusiasm
Comparable units before ranking
Provenance beside every candidate
No fake supplier certainty

Questions

Is it tied to one marketplace?

No. The public engine is marketplace-agnostic and normalises evidence from different sources into a comparable model.

How does it handle duplicate offers?

It includes cross-market deduplication so repeated or near-identical offers do not dominate the ranked candidate list.

Does ranking equal supplier verification?

No. It ranks candidates from observed evidence and provenance; supplier verification remains a separate procurement step.

Next exhibit — 05
Git Privacy Scanner →