Starting point
A technical wholesaler in southern Germany with screws, cap nuts, hydraulic components and tools. 280,000 products, three brand worlds in parallel, volume tiers, technical datasheets per product. Daily revenue in the six-figure range.
The existing standard search delivered measurably weak numbers:
- 38% zero-result rate on search-driven traffic
- 0.9% conversion on search sessions (industry median: 2.8%)
- Avg. response time 340 ms
- Manual synonym maintenance: a two-person team, around 8 h per week
Goal
First: get the zero-result rate below 15%. Second: at least double conversion on search traffic. Third: automate synonym maintenance, so the team has time for assortment decisions instead of day-to-day upkeep.
Implementation
Day 0–1: setup
API integration into the Shopware backend, full catalog indexing in 14 hours (large image volume, technical datasheets co-indexed). Frontend embedded as a widget, no UI changes to the shop. Parallel operation with the standard search for A/B testing.
Day 2–7: tuning
Together with the customer team:
- Imported top 200 zero-result queries from the last 90 days
- Activated industry material mappings (V2A/A2/1.4301 and 15 more families)
- Reviewed compound-word decomposition for “highpressurehose”, “stainlessnut” etc.
- Configured re-ranking on stock level and margin class
Day 8–14: A/B with 50/50 traffic split
Both searches live, alternating. One week. Daily measurement.
Result
| Metric | Standard search | Eywora |
|---|---|---|
| Zero-result rate | 38% | 9% |
| Avg. response time | 340 ms | 52 ms |
| CTR position 1–3 | 21% | 38% |
| Conversion on search | 0.9% | 1.4% |
| Avg. basket value | €184 | €206 |
What’s not on the marketing slides
Three points we want to share honestly:
- The first 3 days were bumpy. Norm mappings didn’t cover every material code the shop uses. Two days of engineering work, then it fit.
- The margin boost was too aggressive. Initially set to 30%, it caused too much ranking shift. Reduced to 12%, then balanced.
- IT had initial GDPR concerns. Resolved in one meeting after we presented the DPA and hosting documentation.
Economic impact
- +€1.4M additional revenue per year from the search funnel
- ~€12K Eywora license per year (Growth + add-ons)
- ~6 h per week of maintenance effort saved
In the customer team’s own words
“We had been treating search as a necessary evil. With Eywora it has become an active conversion driver, and we spend half our time on it.”