FireHydrant
for LuumenAI
On-call, escalation, and timelines from FireHydrant beside the fix.
Keep FireHydrant in step with the fix. LuumenAI sees open incidents and who is on call, escalates with context attached, and keeps the timeline updated as governed actions run — so the record matches what actually happened.
The FireHydrant toolbox
16 tools: 8 read, 8 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadList open incidentsCurrent incidents with severity, responders, and timelines.
- ReadWho is on callResolve the schedule for a service before you page anyone.
- ReadGet incident timelineEvery event on an incident, in order.
- ReadList servicesServices and their current status.
- ReadGet escalation policyWho gets paged, in what order.
- ReadList schedulesOn-call rotations and overrides.
- ReadGet responder statusWho has acknowledged and who has not.
- ReadSearch past incidentsSimilar incidents and how they were resolved.
- WriteAcknowledge incidentTake ownership of an incident from the session. Approval by default
- WritePage a responderEscalate to a person or team with the context attached. Approval by default
- WritePost timeline noteAppend findings and actions to the incident timeline. Approval by default
- WriteResolve incidentClose an incident with the summary attached. Approval by default
- WriteReassign incidentHand off to another responder or team. Approval by default
- WriteAdd responderPull another person into the incident. Approval by default
- WriteCreate maintenance windowSuppress paging for planned work. Approval by default
- WriteOverride on-callSwap the on-call for a bounded period. Approval by default
One prompt, start to finish
What a governed FireHydrant run looks like inside Luumen.
Questions
Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — acknowledge incident, page a responder, post timeline note, resolve incident, and more — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to FireHydrant — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
PagerDutyOn-call, escalation, and timelines from the session.
OpsgenieOn-call, escalation, and timelines from Opsgenie beside the fix.
incident.ioRead incident context on demand, and make changes as approved steps.
RootlyRead Rootly incidents and action items, then update an incident after you approve it.Put FireHydrant to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.