The use case: how Atlassian deploys turbopuffer
Atlassian uses turbopuffer, deployed in its own AWS and GCP environments, as the semantic search engine behind Rovo. It indexes Jira tickets, Confluence pages, Google Drive documents and metadata with one namespace per customer, powering user-facing search and context retrieval for AI agents.
More reported results
Figures published in turbopuffer’s case study. They are not independently measured by usedby.
60ms p90 latency
96% average recall@10
In the customer’s words
turbopuffer gives us the foundation to build profitable AI. We believe in the architecture and we believe in the team.Other AI tools used by Atlassian
Other public relationships recorded on usedby.
ClaudeConfirmed
IntercomConfirmed
IvoConfirmed
SentryConfirmed
Stripe PaymentsConfirmed
UniphoreConfirmedturbopuffer users in DevTools & Infrastructure
Companies in the same sector, with public evidence.
See all turbopuffer customers
Go straight to the source
Based on turbopuffer’s published case study. We check the public evidence; the results are reported by the vendor.
turbopuffer.com- Last checked
- Nov 12, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 19%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 Atlassian.
- Atlassian uses turbopufferChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Since moving turbopuffer into production, the combined effort has brought Atlassian's p90 semantic search latency from 125ms → 60ms while increasing average recall from 90% → 96%+.