Introducing Observability Alerts for Mastra Platform

Set thresholds for cost, tool failures, model latency, token usage, and eval scores.

Patrycja Jenkner-Sar +1·

Nov 19, 2026

·

3 min read

You can now set observability alerts and get notified when model costs exceed limits, error rates climb, or eval scores drop. Send notifications to Slack, Discord, Microsoft Teams, email, webhooks, PagerDuty, or incident.io.

You can configure alerts for:

  • Errors and volume: error rate, number of errors, total count of matching traces or spans.
  • Latency: duration, time to first token, time to first chunk.
  • Token usage: total, input, output, reasoning, cached tokens.
  • Cost and eval scores: spend, the average score from a scorer you choose.
Setting up an observability alert in Mastra Platform and getting notified in Slack.

You could already create incident alerts in Mastra Platform to find out when a deploy failed or a service crashed. Observability alerts let you know when your agents' behavior falls outside the limits you set, even when the service is running normally. You get an alert before your bill gets too high or a user reports a problem.

Previously, you could watch the Metrics page yourself or export traces and build an alert in a tool like Datadog or Grafana. Now you can create alerts directly in Mastra Platform.

Get started

Set up your app to send traces to Mastra Platform. Run your agent and check that you can see its traces in your project.

noteOnly organization admins can create, edit, and delete alerts. Members and viewers have read-only access.

Open the Mastra Platform dashboard and choose Alerts from the sidebar menu. Select New alert, then Observability alert, and choose a template.

For example, choose Tool failures to monitor how often each tool fails.

For your own alert, choose your project, set a threshold, and pick where to send notifications.

You can check the threshold across all matching traffic, or separately for each agent, tool, model, or user.

Use the Backtest chart to see when the rule would have opened and closed on recent traffic.

Adjust the threshold if needed, then select Create alert. Mastra checks enabled rules every five minutes.

To write your own query and condition from scratch, select Start blank instead of a template.

You can also create an alert from the Metrics dashboard. Just click the bell icon on a chart.

For more information and full configuration options, see:

Share on X or LinkedInPatrycja Jenkner-SarPatrycja Jenkner-SarProduct Marketer & Content Engineer

Patrycja Jenkner-Sar is a product marketer and content engineer at Mastra. Previously, she was a product marketer at neptune.ai, an experiment tracker for machine learning teams, and is focused on translating complex functionality into clear value for developers and technical audiences.

All articles by Patrycja Jenkner-Sar →Alex BookerAlex BookerHead of Developer Experience

Alex Booker is the Head of Developer Experience at Mastra, where he helps developers understand and build agent systems with Mastra. He hosts weekly workshops with members of the team and publishes videos on the Mastra YouTube channel. Outside of Mastra, he's a proud Londoner and a keen cyclist, though his legs have not yet caught up with his enthusiasm!

All articles by Alex Booker →

More on Observability

All postsBlogNov 5, 2026

Introducing Latency Metrics for Mastra Observability

Track user experience through TTFT and TTFC.

BlogOct 28, 2026

Introducing Span Queries

Find the most common failures for your coding agent to fix.

BlogOct 21, 2026

Get started with Mastra Observability

Add native traces and evals to your Mastra agents in minutes