The use case: how Canals deploys Elastic Cloud
Canals, which builds AI for wholesale distributors, uses Elastic Cloud to run a hybrid product-matching engine that combines keyword, dense vector, and sparse vector retrieval in a single index. Customer requests such as emails, PDFs, and spreadsheets are matched to the right catalog product, with a downstream ranking layer narrowing candidates to the top results.
More reported results
Figures published in Elastic Cloud’s case study. They are not independently measured by usedby.
In roughly 90% of cases the system is confident enough that it does not show a list at all
serving on the order of 400,000 queries a day
On the products that do exist, recall reached 98%
Precision starts above 75% from the first interactions and climbs over a couple of weeks of usage
In the customer’s words
Elasticsearch never blocked anything or slowed anything down. It let us run all of our experiments and all of our iterations and get to where we are today, and we're still iterating. Elasticsearch makes that easy. We could focus on building search rather than maintaining clusters.Other companies using Elastic Cloud
Customers across industries, with public evidence.
See all Elastic Cloud customersGo straight to the source
Based on Elastic Cloud’s published case study. We check the public evidence; the results are reported by the vendor.
elastic.co- Last checked
- Nov 13, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 63% to 96%Checked
The figure is on the page; its label is our wording.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Canals.
- Canals uses Elastic CloudChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Canals, which builds AI for wholesale distributors, runs a hybrid keyword-and-vector product-matching engine on Elasticsearch that lifted top-3 match accuracy from 63% at launch to 96% today, with roughly 90% of matches now resolved without a human ever picking from a list.






