Outage report
How do we take an outage report from any channel, match it to the premise and any known event, send the ticket to the outage system, and keep the customer updated by text?
Match the report to the premise and the event before anyone types a ticket. Callvu identifies the customer from the phone number, the account or the address, prefills the premise and the meter, classifies the report against the outage management system's known events (a known outage at the feeder, a single-premise trouble, a partial power or flicker, a downed wire that is a safety emergency), captures the few details the classification needs (the time it started, whether neighbors are affected, any hazard), writes the ticket or the event association to the outage management system and the CIS, and sends the customer the estimated restoration and the updates by text under the consent on the account. No agent re-keys an address.
In scopeSimpleCallvu moves: prefill, classify, write back
Last updated November 7, 2026.
The problem today
Four thousand customers called about the same feeder, and each one spelled their address to an agent.
A storm takes out a feeder. The calls come in by the thousand; the IVR asks for the account number the customer does not have in the dark; the agent asks for the address, types it, and creates a ticket the outage system already has. Nobody tells the customer when the power will be back, so they call again. The downed wire in the backyard waits behind the calls about the flicker.
An outage report has a shape: the premise, matched from whatever identifier the customer has; the known event at that premise's feeder or transformer; the safety classification that sends a downed wire or a fire to dispatch ahead of everything; the details the outage system needs; the customer's consent to be texted, and the estimated restoration time that stops the second call. The outage management system is the record for the event, the CIS for the customer.
The report that matches itself to the event is the one the outage system can use.
How it runs
From the requestto the system of record.
A customer reports an outage by call, text, app, website or an AI assistant. Callvu identifies them and opens the report.
- Customer
- Reports from any channel, confirms the premise, answers the few questions and receives text updates.
- Outage management and dispatch
- Receive the ticket or the event association, and the safety emergencies first.
- Callvu
- Identifies, prefills, classifies, writes and sends updates.
Prefill the premise
The customer is identified from the calling number, the account, the address or the login; the premise, the meter and the feeder are prefilled from the CIS and the smart meter's last-gasp signal where one exists, and the customer confirms the address rather than reading it out.
Classify the report
The report is classified against the outage management system: a known event at the premise's feeder or transformer (the customer is attached to it and told the estimated restoration), a new single-premise trouble (a ticket is created), a partial power or flicker (a power quality ticket), or a safety hazard (a downed wire, sparking, a fire, a smell of gas) that routes to dispatch immediately ahead of the queue with the emergency script.
Capture what the classification needs
Only the details the ticket type needs are asked: when it started, whether neighbors are out, whether a breaker was checked, the hazard's location; a medical or life-support flag on the account is attached to the ticket so restoration priority applies.
Write back and update
The ticket or the event association is written to the outage management system and the report to the CIS, the system of record for the customer; the customer receives the estimated restoration time and the updates (crew assigned, restored, delayed) by text where the account's consent allows, and a restoration confirmation asks whether power is back so a nested outage is caught.
Where it ends: Every report was matched to the premise and the known event, the hazards went first, the outage system got one ticket per trouble, and the customer was told the restoration time without calling twice. The Decision Trace shows the classification and the consent check; the Audit Trace shows the report, the write and each text with time.
Runtime enforcement
What is enforcedwhile the work runs.
The regulations preloaded in Callvu Studio and the bank's own policies, applied as steps that run, not lines in a binder. A step that breaks a rule does not run, so a completed run was compliant.
The handoff
Between the front doorand the back office.
The front door
Call, text, app, website or an AI assistant; the IVR texts a link so the customer reports on their phone.
The back office
Dispatch sees hazards first; the outage system holds one ticket per trouble; agents take only what needs a person.
The Decision Desk
- A report that matches two premises, a hazard the customer cannot locate, or a life-support customer in a long event goes to the outage desk in the Decision Desk with the record and only the allowed outcomes.
Proof
In scope.Proof at scale, not one process at a time.
The kind of process Callvu runs in production for customers in this industry. Ask for a reference on this exact process. The results below are the industry's published proof; each claim code links to its record on agents.callvu.com.
More than 1,000 processes are live across Callvu customers.
Across Callvu customers
PSEG Long Island runs start, stop and move service on Callvu, live in 4 weeks.
Across Callvu customers
Questions
What buyers ask next,answered plainly.
Does the customer need an account number?
No. The calling number, the address or the login identifies them, and the premise is prefilled from the CIS; they confirm rather than spell.
What happens to a downed wire report?
It is classified as a safety hazard and dispatched immediately, ahead of the queue, with the emergency script.
How is the customer updated?
By text with the estimated restoration and each change, under the consent on the account, with a confirmation at restoration.
Related processes
Bring this process, or the one that costs you most.
We build it against your policies and your systems, train your team and stay with you through launch. You are live in weeks.