8 min
How to Monitor LLM Call Latency in Production Workflows
Monitor LLM call latency in production workflows with traces, model percentiles, token usage, costs, errors, and workflow context.
llm-observabilityperformance-monitoring
Blog
Engineering insights on observability, distributed tracing, and production debugging.
6 posts tagged performance-monitoring
8 min
Node.js monitorEventLoopDelay and eventLoopUtilization
Use Node.js monitorEventLoopDelay and eventLoopUtilization to measure event-loop lag, export useful metrics, and debug blocking production code.
nodejsperformance-monitoring
4 min
Your API Just Threw a 500. Here's How to Actually Fix It.
Your API threw a 500 at 3 AM. A systematic approach to diagnose, trace, and fix production API errors without the panic and guesswork.
apmdebugging
4 min
Zero-Cost Production Visibility: APM Without the Datadog Bill
Get production visibility without the Datadog bill. Free-tier APM setup with OpenTelemetry for freelancers and small teams who need traces, not invoices.
distributed-tracinggolang
8 min
Node.js Performance Monitoring Checklist for Production Apps
Use this Node.js performance monitoring checklist to trace requests, spot event loop lag, catch regressions, and inspect runtime state without redeploying.
nodejsperformance-monitoring
5 min
Debug Production Issues 10x Faster with Tracing
Debug production issues 10x faster with distributed tracing. Track requests across microservices, find bottlenecks, and resolve errors without log diving.
debuggingdistributed-tracing