The Resolution Layer · Case Study in BriefEKOM
A specialty footwear retailer.
A full-catalog, no-schema read across running, hiking, comfort, and kids' footwear — one of a set of anonymized EKOM analyses. What surfaced, and where it leads.
Lead finding · discovery & trust
Two women's shoes read like men's. Three men's shoes read like women's.
Live product descriptions are cross-wired across gender for the same running-shoe model — the copy exists, it's just attached to the wrong product, and it's the first thing a shopper reads on the page. Separately, a hiking sandal carries a children's sandal's description instead of its own.
Also surfaced
Brand mistagged as a rival
Two items from one athletic brand carry a rival brand's tag instead of their own — invisible in the correct brand's filter, visible under a brand that didn't make them.
A routing code that cross-wires gender
An internal code that encodes gender and style together carries the wrong value on six SKUs across a handful of running-shoe models — the structural root behind several of the filter leaks below.
Gender-filter leaks
Unisex socks filed as women's despite their own unisex spec; a sandal and a slipper missing the gender prefix their siblings carry; a unisex kids' item filed under boys-only despite carrying both boys' and girls' tags.
Broken links & duplicated signals
A doubled-letter typo in two product handles produces a 404; sale status is stored in two places on many items, with real risk of the two disagreeing.
How EKOM read it. With no schema and no manual setup, the engine profiled the catalog and read it in full rather than sampling — which is what surfaced a routing-code pattern concentrated in a handful of styles instead of averaging away.
From diagnosis to channel-ready. This pass read and diagnosed. The same understanding powers what follows — re-mapping the cross-wired descriptions, correcting the mistagged brand and the routing code at its source, and holding the line at intake as new styles and colorways arrive.