Relvy analyzes application traces from Datadog

support@relvy.ai
<-- Back to Blog

Alerts from golden signals - latency, request counts and errors are critical to monitoring production systems. Engineers often visit Application Performance Monitoring (APM) dashboards and look at distributed tracing data to get to the bottom of these alerts. 

We are happy to announce that Relvy’s debugging AI is now equipped to analyze APM traces and metrics from Datadog. Relvy queries for appropriate traces based on the information in production alerts, and picks out exemplar traces to look deeper into. It looks at the spans in such traces to understand the contributing factors to latency and errors. This trace analysis is combined with our analysis of other APM metrics, dashboards and logs to provide an accurate root cause analysis summary. Please see our video below to see it in action.

Engineers get answers to the following questions right on Slack without having to look up any data manually:

  • What spans are contributing to latency, or erroring out?
  • Which other services / endpoints are affected?
  • Is there anything important in the logs for affected traces?

Relvy automatically discovers APM metrics on connected datadog instances, and performs trace analysis for appropriate alerts. No additional configuration is needed. Our APM analysis capability is currently rolled out to customers using Datadog. Support for other tools is coming soon.We’ve paired our cost effective custom tuned language models which operate at 1/200th the cost of existing foundational models to make 24/7 agentic AI monitoring and debugging a reality. Get started instantly and see how Relvy can drastically reduce debugging time and costs, transforming your engineering processes today. https://www.relvy.ai/get-started