# How Consensus uses Zilliz

**~45 ms** P99 dense retrieval latency in production across

As published on [zilliz.com](https://zilliz.com/customers/consensus). Captured by usedby on 2026-10-06.

- Company: [Consensus](https://www.usedby.ai/companies/consensus.md)
- Tool: [Zilliz](https://www.usedby.ai/tools/zilliz.md)

## What the story says

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.

Summary written by usedby from the source page, in English. The figures are those of Zilliz and Consensus, not ours.

> 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.

- **~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”

> 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

## What usedby checked

We compared the story with its live page on 2026-10-06.

- Checked: the figure ~45 ms is on the page; its label is our wording.
- Checked: the passage quoted above is copied word for word from the page, near the name of Consensus.
- Checked: each number in our summary is printed on the page.
- Checked: Consensus uses Zilliz. Confirmed line. Latest check across sources: 2026-10-06.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/consensus-zilliz · How we check: https://www.usedby.ai/methodology