Observability
Tracing, logging and metrics for understanding what agents do in production.
20 posts
Get started with Mastra Observability
Add native traces and evals to your Mastra agents in minutes
Oct 15, 2026BlogIntroducing Trace Queries
Find slow or failed runs for your coding agent to fix.
Oct 14, 2026BlogIntroducing Trace Imports for Mastra Platform
Import and inspect existing trace history.
Oct 13, 2026BlogIntroducing the Metrics API for Mastra Platform
Query cost, latency, and errors by agent, thread, or time.
Oct 12, 2026BlogIntroducing Thread View for Mastra Observability
Read agent traces in the context of the conversation that produced them.
Sep 18, 2026BlogIntroducing the Feedback API Endpoint for Mastra Observability
Query feedback by region, environment, thread and source.
Sep 17, 2026BlogIntroducing Incident Alerts for Mastra Platform
Real-time updates for failed deploys and crashed services.
Sep 14, 2026BlogIntroducing Server Health for Mastra Platform
Monitor server requests and inspect by path, status, or latency.
Aug 27, 2026BlogIntroducing Token Cost Control for Mastra Agents
Real-time spending caps configurable by thread, user, session, org, and more.
Aug 16, 2026ArticleLangfuse vs LangSmith: a hands-on comparison for LLM observability
A hands-on Langfuse vs LangSmith comparison covering tracing, evals, prompt management, integrations, self-hosting, and pricing for LLM observability.
Aug 4, 2026BlogIntroducing Agent Feedback and Feedback Analytics
Capture human feedback for every agent response and query them by agent, source, or time.
Jul 27, 2026BlogAnnouncing Trace Intelligence
Group traces into clusters.
Jul 23, 2026ArticleTrace ID explained: what it is, how it works, and when to use it
Learn what a trace ID is, how it differs from a correlation ID, and how to implement distributed tracing with OpenTelemetry in your services.
Jul 10, 2026BlogWhat is LLM observability? A span-by-span breakdown
LLM observability records what an agent did at the level of individual model calls and tool executions. This reads the trace of a live agent run span by span from storage, shows what a hallucination and a failed tool call look like, covers where the OpenTelemetry GenAI conventions stand in mid-2026, and walks the four dials that control tracing cost in production.
Jun 22, 2026ArticleAI agent observability: a complete guide for production teams
Learn how AI agent observability works, its core pillars, best practices for tracing and evals, and how to monitor agents reliably in production.
Jun 22, 2026ArticleLLM observability platform: a complete guide for AI teams
Learn how to instrument, monitor, and evaluate LLM apps in production with traces, metrics, evals, and the right observability platform for your stack.
May 13, 2026BlogAnnouncing Mastra Observability
Production observability for every Mastra project.
May 5, 2026BlogIntroducing ClickHouse Support for Mastra Observability
Make your Mastra application production-ready with observability storage that scales.
Apr 1, 2026BlogIntroducing Metrics and Logs
Mastra Studio now supports logs, traces, and metrics, so you can understand how your agents behave in production.
Sep 30, 2025BlogMastra now supports AI Tracing
Mastra introduces AI Tracing: filter out noise and use multiple observability platforms.
