Decision owner
Control-room operator
The named role remains accountable for the consequential decision.
Energy & Utilities
Designed for Control-room operator
Help control-room operators cut through alarm storms by correlating SCADA events with network topology, weather, and field work into a ranked probable-cause narrative, while every switching action stays an operator decision.
Contract ENE-03 · primary aggregate GridEvent · mode loading
Decision brief
This brief starts with the decision, evidence, and accountable owner. The guided workflow then shows how the recommendation was produced.
The evidence and control points that shape this recommendation.
Decision owner
Control-room operator
The named role remains accountable for the consequential decision.
Governed evidence
6 record types
Structured records and cited text ground the recommendation.
Workflow
5 controlled stages
Each transition records its input, output, status, and audit context.
Human controls
1 approval gate
Approval gates prevent the copilot from making consequential decisions.
A summer storm produces 214 alarms in six minutes; the copilot correlates them into three grid events, attributes the largest to a lightning strike two kilometres from a failed recloser, rules out a fourth cluster as planned crew switching, and proposes a back-feed restoration that the operator reviews and executes for 4,800 customers..
Help control-room operators cut through alarm storms by correlating SCADA events with network topology, weather, and field work into a ranked probable-cause narrative, while every switching action stays an operator decision.
Executed switching order and updated event disposition gives Control-room operator the evidence needed to begin the final governed business outcome, with the decision trail retained for review.
Step 1 of 5
| Field | Value |
|---|
| Field | Value |
|---|
The output appears here immediately. More technical evidence remains available below.
The demonstration keeps deterministic controls, AI assistance, and approval separate.
Source systems enforce identity, workflow order, policy filters, and record updates.
Retrieval and generation assemble relevant evidence into a cited recommendation or draft.
Control-room operator verifies material claims and approves the consequential action.
Run the stages in order before using the Copilot. Every stage explains what happens, why it matters, the evidence it uses, and the complete API request and response.
Automated stage
What happens: SCADA integration service performs ingest alarms and protection operations using Alarm stream with device points and quality flags and produces Time-ordered alarm set for the control area. The transition is deterministic and does not require autonomous model approval.
Why it matters: Time-ordered alarm set for the control area gives Correlation agent the evidence needed to begin Correlate alarms into a single grid event, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/ingest-alarms-and-protection-operations
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Correlation agent performs correlate alarms into a single grid event using Alarms, topology snapshot, and timing windows and produces GridEvent with the affected network element. The transition is deterministic and does not require autonomous model approval.
Why it matters: GridEvent with the affected network element gives Cause ranking agent the evidence needed to begin Rank probable causes with context, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/correlate-alarms-into-a-single-grid-event
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Cause ranking agent performs rank probable causes with context using Weather, field work logs, and asset history and produces Ranked hypotheses such as lightning, vegetation, or crew switching. The transition is deterministic and does not require autonomous model approval.
Why it matters: Ranked hypotheses such as lightning, vegetation, or crew switching gives Restoration agent the evidence needed to begin Propose restoration switching, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/rank-probable-causes-with-context
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Restoration agent performs propose restoration switching using Topology and load estimates and produces OperatorActionProposal with predicted impact. The transition is deterministic and does not require autonomous model approval.
Why it matters: OperatorActionProposal with predicted impact gives Control-room operator the evidence needed to begin Execute operator-approved switching, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/propose-restoration-switching
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Human approval required
What happens: Control-room operator performs execute operator-approved switching using Proposal with risk notes and produces Executed switching order and updated event disposition. A named human approver must review the evidence before the transition completes.
Why it matters: Executed switching order and updated event disposition gives Control-room operator the evidence needed to begin the final governed business outcome, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/execute-operator-approved-switching
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Run a stage to see its explanation, evidence, full request, and full response.
Ask a question and receive an answer grounded in retrieved GridEvent evidence.
Select a starter question or enter your own.
Loaded live from /api/config, /api/domain/model, and
/api/domain/sample.
gridEvents/tenantId + /controlAreaIdA summer storm produces 214 alarms in six minutes; the copilot correlates them into three grid events, attributes the largest to a lightning strike two kilometres from a failed recloser, rules out a fourth cluster as planned crew switching, and proposes a back-feed restoration that the operator reviews and executes for 4,800 customers.
| Container | Role | Hierarchical partition key | Document types |
|---|---|---|---|
gridEvents |
Primary | /tenantId + /controlAreaId |
GridEvent, ScadaAlarm, NetworkTopologySnapshot, WeatherObservation, FieldWorkLogEntry, OperatorActionProposal |
| Type | Container | Partition key | Identifier pattern | Embedding fields |
|---|---|---|---|---|
GridEvent |
gridEvents |
/tenantId + /controlAreaId |
gridevent::{controlAreaId}::{eventId} |
None |
ScadaAlarm |
gridEvents |
/tenantId + /controlAreaId |
alarm::{controlAreaId}::{alarmId} |
None |
NetworkTopologySnapshot |
gridEvents |
/tenantId + /controlAreaId |
topology::{controlAreaId}::{snapshotUtc} |
None |
WeatherObservation |
gridEvents |
/tenantId + /controlAreaId |
weather::{controlAreaId}::{observationUtc} |
None |
FieldWorkLogEntry |
gridEvents |
/tenantId + /controlAreaId |
worklog::{controlAreaId}::{logId} |
activityNarrativeVector |
OperatorActionProposal |
gridEvents |
/tenantId + /controlAreaId |
proposal::{controlAreaId}::{proposalId} |
riskNotesVector |
Read alarms and topology for the control area within the correlation window in one partition query.
gridEvents
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.controlAreaId = @controlAreaId AND c.type IN ('ScadaAlarm','NetworkTopologySnapshot') AND c.raisedUtc >= @windowStartUtc ORDER BY c.raisedUtc ASC
Test whether lightning or wind in the same grid cell explains the event timing.
gridEvents
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.controlAreaId = @controlAreaId AND c.type = 'WeatherObservation' AND c.observationUtc BETWEEN @windowStartUtc AND @windowEndUtc AND c.lightningStrikeCount > 0 ORDER BY c.lightningStrikeCount DESC
Rule out alarms caused by crews performing planned switching.
gridEvents
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.controlAreaId = @controlAreaId AND c.type = 'FieldWorkLogEntry' AND c.plannedSwitching = true AND c.startUtc >= @windowStartUtc ORDER BY c.startUtc DESC
Prioritize unresolved events by customers affected for the operator console.
gridEvents
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.controlAreaId = @controlAreaId AND c.type = 'GridEvent' AND c.dispositionState != 'resolved' ORDER BY c.customersAffected DESC