The use case: how Pylon deploys turbopuffer
Pylon uses turbopuffer for multi-tenant semantic search over customer documentation, knowledge bases, and past support tickets. It powers AI features such as AskAI, knowledge gap detection and feature request clustering, with each Pylon customer mapped to its own namespace for data isolation.
More reported results
Figures published in turbopuffer’s case study. They are not independently measured by usedby.
24ms P90 query latency
300M+ documents indexed
20k+ namespaces with no per-namespace cost overhead
In the customer’s words
We were running turbopuffer in production within two to three days of getting our API key.Other AI tools used by Pylon
Other public relationships recorded on usedby.
Explore Pylon’s AI stack
turbopuffer users in Sales Tech & CRM
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: 3 daysChecked
Printed word for word on the page, near the name of Pylon.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Pylon.
- Pylon uses turbopufferChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
They had turbopuffer running in production in just 3 days, compared to weeks configuring OpenSearch - and that's with the time Bennett spent writing his own Go client (the official turbopuffer Go client library didn't exist yet).