# How Read AI uses Zilliz

**5×**: “Read AI has achieved a 5× speedup in agentic search across diverse data sources”

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

- Company: [Read AI](https://www.usedby.ai/companies/read-ai.md)
- Tool: [Zilliz](https://www.usedby.ai/tools/zilliz.md)

## What the story says

Read AI uses Milvus as the central vector database behind its semantic search, storing embeddings of meetings, chats, emails and CRM data. It runs filtered vector search in a single multi-tenant cluster to retrieve related conversations, action items and documents for its users.

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

> Since deploying Milvus and alongside the company’s launch of its enterprise search tool Ask Read, Read AI has achieved a 5× speedup in agentic search across diverse data sources, maintaining consistent retrieval latency of around 20- 50ms, even when handling queries with complex filters.

- **20- 50ms**: “maintaining consistent retrieval latency of around 20- 50ms, even when handling queries with complex filters”

> We've got millions of monthly active users and all of the underlying data when we're trying to go find related conversations, find updates to an action item, find referenced documents...Milvus serves as the central repository and powers our information retrieval among billions of records.
>
> Rob Williams, Co-Founder and CTO at Read AI

## What usedby checked

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

- Checked: the figure 5× is printed word for word on the page, near the name of Read AI.
- Checked: the passage quoted above is copied word for word from the page, near the name of Read AI.
- Checked: Read AI 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/read-ai-zilliz · How we check: https://www.usedby.ai/methodology