Monitoring AI Applications with Azure Monitor and Application Insights
Configure alerts for latency spikes, error rate increases, and token usage anomalies to catch issues before they impact users.
8 articles
Configure alerts for latency spikes, error rate increases, and token usage anomalies to catch issues before they impact users.
Monitor these essential AI metrics: latency (p50, p95, p99), token consumption per request, error rates by model and endpoint, cache hit rates for…
Observability in 2022 moved beyond simple monitoring to true understanding of system behavior. OpenTelemetry became the standard for instrumentation. SLOs…
Application Insights provides the deep observability needed for modern applications. Combined with Azure Monitor's broader capabilities, it enables…
There are two ways to publish custom metrics: Application Insights SDK : For application level metrics Azure Monitor REST API : For any metric source Use…
Application Insights is the monitoring tool that pays you back in proportion to how much you invest in it. Out of the box you get…
Application Insights is essential for production observability.
First thing I do on any new Azure-hosted application I'm asked to look at: open Application Insights and see what's actually happening. Half the time, "the…