Elevated errors and latency on the US data plane API
major- Started
- Sep 30, 7:36 AM EDT
- Resolved
- Sep 30, 8:54 AM EDT
- Duration
- 1h 18m
Braintrust's updates (4)
- investigating · Sep 30, 7:36 AM EDT
We are investigating elevated errors affecting the Braintrust control plane APIs. Some users may experience failures when accessing projects, prompts, settings, or creating new resources.
- investigating · Sep 30, 7:50 AM EDT
We are investigating elevated error rates and increased latency on the US centrally-hosted data plane. Some requests, including function invocations, BTQL queries and loading logs or experiments in the UI, may fail or time out.
- monitoring · Sep 30, 8:35 AM EDT
We have applied a fix and are monitoring the results.
- resolved · Sep 30, 8:54 AM EDT
The issue has been resolved.
What our checks recorded
We checked Braintrust 15 times from Braintrust's start time to its resolution, once every five minutes. Every one of them reached Braintrust's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 139 ms, against 116 ms over the 24 hours before. Braintrust posted the incident at Sep 30, 7:36 AM EDT.
Updates are Braintrust's own words from its status page (status: resolved); we never add an inferred cause.