Decision owner
Customer
The named role remains accountable for the consequential decision.
Energy & Utilities
Designed for Utility customer
Help a utility customer understand a surprising bill and act on it by explaining usage drivers, tariff mechanics, and eligible programs in plain language, with confirmation before any tariff switch or program enrollment.
Contract ENE-02 · primary aggregate CustomerEnergyAccount · 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
Customer
The named role remains accountable for the consequential decision.
Governed evidence
5 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 customer's bill rises 62 percent in August; the advisor attributes 38 percent to cooling degree days, 19 percent to a new on-peak window after a rate change, shows the three hottest afternoons that drove peak demand, and enrolls the customer in a smart-thermostat demand-response program after they confirm the terms..
Help a utility customer understand a surprising bill and act on it by explaining usage drivers, tariff mechanics, and eligible programs in plain language, with confirmation before any tariff switch or program enrollment.
Submitted change request with confirmation record gives Customer 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.
Customer 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: Utility customer performs ask why the bill changed using Question in the self-service app or IVR and produces Classified billing or usage intent. The transition is deterministic and does not require autonomous model approval.
Why it matters: Classified billing or usage intent gives Usage analytics agent the evidence needed to begin Decompose the bill into drivers, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/ask-why-the-bill-changed
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Usage analytics agent performs decompose the bill into drivers using Bill line items and interval usage summaries and produces Driver attribution such as weather, rate change, or usage shift. The transition is deterministic and does not require autonomous model approval.
Why it matters: Driver attribution such as weather, rate change, or usage shift gives Energy advisor the evidence needed to begin Explain tariff mechanics in plain language, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/decompose-the-bill-into-drivers
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Energy advisor performs explain tariff mechanics in plain language using Active tariff definition and time-of-use breakdown and produces Cited explanation with the customer's own numbers. The transition is deterministic and does not require autonomous model approval.
Why it matters: Cited explanation with the customer's own numbers gives Eligibility agent the evidence needed to begin Match eligible programs and alternatives, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/explain-tariff-mechanics-in-plain-language
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Eligibility agent performs match eligible programs and alternatives using Premise, usage profile, and program criteria and produces Ranked tariff and program options with projected savings. The transition is deterministic and does not require autonomous model approval.
Why it matters: Ranked tariff and program options with projected savings gives Customer the evidence needed to begin Confirm tariff switch or enrollment, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/match-eligible-programs-and-alternatives
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Human approval required
What happens: Customer performs confirm tariff switch or enrollment using Proposed tariff change or program enrollment and produces Submitted change request with confirmation record. A named human approver must review the evidence before the transition completes.
Why it matters: Submitted change request with confirmation record gives Customer 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/confirm-tariff-switch-or-enrollment
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 CustomerEnergyAccount evidence.
Select a starter question or enter your own.
Loaded live from /api/config, /api/domain/model, and
/api/domain/sample.
customerEnergyAccounts/tenantId + /serviceAccountIdA customer's bill rises 62 percent in August; the advisor attributes 38 percent to cooling degree days, 19 percent to a new on-peak window after a rate change, shows the three hottest afternoons that drove peak demand, and enrolls the customer in a smart-thermostat demand-response program after they confirm the terms.
| Container | Role | Hierarchical partition key | Document types |
|---|---|---|---|
customerEnergyAccounts |
Primary | /tenantId + /serviceAccountId |
CustomerEnergyAccount, IntervalUsageSummary, BillStatement |
tariffCatalog |
Reference | /tenantId + /serviceClassCode |
TariffDefinition |
efficiencyProgramCatalog |
Reference | /tenantId + /programSegmentCode |
EfficiencyProgram |
| Type | Container | Partition key | Identifier pattern | Embedding fields |
|---|---|---|---|---|
CustomerEnergyAccount |
customerEnergyAccounts |
/tenantId + /serviceAccountId |
account::{serviceAccountId} |
None |
IntervalUsageSummary |
customerEnergyAccounts |
/tenantId + /serviceAccountId |
usage::{serviceAccountId}::{summaryDate} |
None |
BillStatement |
customerEnergyAccounts |
/tenantId + /serviceAccountId |
bill::{serviceAccountId}::{billPeriodEnd} |
None |
TariffDefinition |
tariffCatalog |
/tenantId + /serviceClassCode |
tariff::{serviceClassCode}::{tariffCode}::{versionLabel} |
tariffSummaryVector |
EfficiencyProgram |
efficiencyProgramCatalog |
/tenantId + /programSegmentCode |
program::{programSegmentCode}::{programId} |
programDescriptionVector |
Read the bill and the matching usage summaries for the period in one partition query.
customerEnergyAccounts
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.serviceAccountId = @serviceAccountId AND c.type IN ('BillStatement','IntervalUsageSummary') AND c.summaryDate >= @billPeriodStart ORDER BY c.summaryDate ASC
Identify the days that drove the on-peak charges in the billing period.
customerEnergyAccounts
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.serviceAccountId = @serviceAccountId AND c.type = 'IntervalUsageSummary' AND c.peakDemandKw > @peakThresholdKw ORDER BY c.peakDemandKw DESC
Knowledge-container query against efficiencyProgramCatalog (partition-aligned to /tenantId + /programSegmentCode): return active programmes whose eligibility criteria the premise and usage profile satisfy; the catalogue is partitioned by customer segment so the read touches one partition.
efficiencyProgramCatalog
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.programSegmentCode = @customerSegmentCode AND c.type = 'EfficiencyProgram' AND c.programStatus = 'open' AND c.eligibilityCriteria.meterType = @meterType ORDER BY c.incentiveValue DESC
Knowledge-container query against tariffCatalog (partition-aligned to /tenantId + /serviceClassCode): load the candidate rate schedules valid for the customer's service class for savings modelling, as a single partition read of that service class.
tariffCatalog
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.serviceClassCode = @serviceClass AND c.type = 'TariffDefinition' AND c.effectiveToUtc > @nowUtc ORDER BY c.versionLabel DESC