How it works
No stage requires a manual handoff — each layer feeds the next automatically:- Collect — events stream in from sources like AWS, Datadog, Slack, and PagerDuty into one Pulse feed.
- Filter and correlate — suppression layers remove duplicates, rate-limited bursts, and flapping resources. Related signals are grouped into clusters, so nine alerts about the same node pool become one item.
- Classify and escalate — every signal gets a category, canonical severity, and actionability score. When a cluster is Critical or High, or the AI marks it actionable, it escalates to an incident automatically.
- Investigate — an AI agent forms explicit hypotheses, tests each one against metrics and logs, and produces a structured report: most likely root cause, evidence chain, and ruled-out theories.
- Resolve and remember — the agent matches your runbooks to the root cause and executes them under the autonomy mode you set (Manual or Auto). Each resolution feeds incident memory, making the next investigation faster.
What you can do
Key concepts
Get started
Connect signal sources
Connect AWS, Slack, Teams, and webhook sources to start feeding Pulse.
Set up webhook integrations
Route alerts from PagerDuty, Datadog, CloudWatch, and more into the response loop.
Add runbooks
Give agents the procedures they can execute during remediation.
See how investigation works
Follow a hypothesis-driven root cause analysis end to end.