Mastra Platform Adds Observability Alerts for AI Agents
Mastra introduced observability alerts that monitor AI agent behavior against configurable thresholds for errors, traffic volume, latency, token usage, model costs and evaluation scores. According to Mastra, alerts can be scoped by agent, tool, model or user and delivered through Slack, Discord, Microsoft Teams, email, webhooks, PagerDuty or incident.io, with enabled rules checked every five minutes.
The update gives agent builders built-in monitoring for operational and quality thresholds, reducing the need to export traces and create separate alerts in tools such as Datadog or Grafana.
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.
Your browser does not support the video tag.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.
#Mastra Platform#Slack#Discord#Microsoft Teams#PagerDuty#incident.io