AgentPulse Docs

Alert Rules

Alert rules watch your metrics and notify you the moment a threshold is breached, so you don't have to stare at a dashboard.

Anatomy of a rule

A rule combines a metric, an operator, a threshold, and a rolling window. The window smooths out one-off blips so the alert that reaches you is one worth acting on.

Metrics

MetricCatches
error_rateA deploy or upstream change breaking runs.
success_rateThe inverse view — alert when it drops below a floor.
avg_latency_msA slow tool or degraded model provider.
failed_runsAbsolute count of failures — useful at high volume.
cost_usdA retry loop or ballooning prompt burning budget.

Operators and windows

Use gt (greater than) or lt (less than) against your threshold, evaluated over the rolling window you choose. For example, error_rate gt 5 over 15 minutes fires when more than 5% of runs in the last 15 minutes failed.

Deduplication and re-arming

AgentPulse deduplicates open alerts — you get one notification per breach, not one per minute. The rule re-arms only after the condition resolves, so you are told once when it breaks and once when it is healthy again.

Delivery channels

Attach one or more channels to a rule — Slack, a generic HTTP webhook, or email. See Notifications to configure them. Delivery is a no-op for any channel that is not configured.