Skip to main content
usedby
ZillizusedbyConsensus

How Consensus uses Zilliz

ConfirmedVendor case study · Checked Oct 6, 2026
View captured proof

The use case: how Consensus deploys Zilliz

Consensus uses Zilliz Cloud as the semantic (dense vector) search layer of its research agent platform, searching over 400M+ scholarly sources. The agent calls it as a tool, and the full collection is rebuilt by bulk import into an idle copy of the collection that is then switched live.

More reported results

Figures published in Zilliz’s case study. They are not independently measured by usedby.

~45 ms

P99 retrieval at ~45 ms across 400M+ vectors

14%

14% higher precision in search results after adding semantic search

27%

the larger embeddings delivered a 27% increase in the quality of papers found

2.5×

4x larger vector dimensions (256 → 1,024) cost only 2.5× the cluster on Zilliz Cloud

In the customer’s words

Our job is to make the best research findable for anyone who uses Consensus. Zilliz Cloud gives our research agent fast, high-quality semantic retrieval, directly widening the evidence it can reach.
Christian Salem, Co-founder & Chief Product Officer, Consensus — Source
Zilliz helps us match people with the right opportunities through fast, relevant AI search.
Ethan Zheng, Co-Founder & CTO, Consensus — Source, captured Oct 17, 2026

Zilliz users in Artificial Intelligence

Companies in the same sector, with public evidence.

ExaConfirmedMiniMaxConfirmedPlaudConfirmedSarvamObservedxAIObserved
See all Zilliz customers

More stories

Go straight to the source

Based on Zilliz’s published case study. We check the public evidence; the results are reported by the vendor.

zilliz.com
Last checked
Oct 6, 2026
zilliz.comCaptured Zilliz case study about ConsensusOpen source capture
What the story claims, and what we checked

What we compared with the page.

  • The passage quoted aboveChecked

    Copied word for word from the page, near the name of Consensus.

  • The numbers in our summaryChecked

    Each one is printed on the page.

  • Consensus uses ZillizChecked

    Confirmed line.

  • The result itselfNot checked

    We quote it; we did not measure it.

A daily bulk import of the entire collection turns a full rebuild from a special project into a nightly job. This also unlocks much faster iteration when testing new embedding models.
From the page. zilliz.com