Datadog Alert Triage Agent with Hermes
Watch it work before it's live
[Triggered] api-gateway 5xx ratio above 2%
TriggeredError ratio 7.4% over the last 5 minutes against a 2% threshold, evaluated across 34 of 36 gateway pods. Triggered 14:07 UTC. Tags env:prod, region:eu-west-1, version:2026.8.4.
Set up in minutes
Connect Datadog
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Severity rules
Which monitors are worth waking someone for - what each severity level means on your services, what counts as fleet wide, your quiet hours, and the monitors you would rather never see in the channel.
Runs on Hermes
Preselected for this page — connect your Hermes account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Why Hermes for this agent
Evidence, not a story
Two or three values with their units and timestamps, plus a log excerpt no longer than three lines. There is no room in the format for a paragraph of interpretation.
The suggestion stays a suggestion
First check points a human somewhere. Nothing gets muted, resolved, restarted or rolled back by the agent, whichever model is sitting behind it.
Before you fork
We have never written down what our severities mean. Can we still use this?
Yes, and it will tell you where the gaps are. When your rules are silent on a monitor it posts the fired, scope and evidence lines, states that the rules do not cover it, and leaves the call to whoever is on call. A fortnight of those notes is a decent first draft of the severity document you have been meaning to write.
Run it with a different agent
Put Datadog Alert Triage Agent to work on Hermes.
Free to start. Guided setup, a staged test run, and a workflow you can change at every step.