Why 34% landed
19 + 11 + 4 = 34
Feature and display, raw coupon lift, and warm-weather demand were stacked by the forecast engine.
Agriculture & Food
Designed for Planner
Give the demand planner a consensus planning surface that reconciles statistical forecast, promotion lifts, open orders and weather-sensitive demand at the item-location level, explains every override, and routes exception-level changes for commercial sign-off.
Contract AGR-03 · primary aggregate PlanningUnitForecast · mode loading
Decision brief
Here is how 34% landed: the forecast engine added 19 points for the approved feature-and-display event, 11 raw points for the overlapping coupon, and 4 points for warm weather. That 34-point stack moves 10,000 units to 13,400. The team must determine how much is real, duplicated, and uncertain.
The evidence and control points that shape this recommendation.
Why 34% landed
19 + 11 + 4 = 34
Feature and display, raw coupon lift, and warm-weather demand were stacked by the forecast engine.
Statistical forecast
10,000 → 13,400
(13,400 - 10,000) / 10,000 = 34%. Calculated upstream, not by GenAI.
Approved promotion
+19 points
Structured feature-and-display plan retained by deterministic rules.
Overlapping coupon
11 → 4 points
A deterministic overlap rule removes seven duplicate points.
Rules-adjusted forecast
+27%
13,400 minus 700 duplicated units produces 12,700 units.
Human-approved forecast
+26%
The planner applies a one-point risk adjustment and approves 12,600 units.
A Midwest retailer scheduled a feature-and-display event and an overlapping digital coupon during an unusually warm Ohio week. The statistical engine stacked those signals and raised the forecast from 10,000 to 13,400 units.
Verify the calculation, remove duplicate promotion lift, review the GenAI evidence summary, and decide whether to approve 12,600 units.
Lock one explainable forecast and hand it to supply planning and procurement.
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.
The forecast engine calculates 34%; deterministic services net promotion overlap, validate workflow order, and lock records.
Hybrid retrieval finds prior minutes and the weather advisory. GenAI synthesizes them into a cited explanation and draft rationale.
The planner evaluates uncertainty, applies the final one-point risk adjustment, approves 26%, and remains accountable for the decision.
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: Combine recent order, point-of-sale, inventory, and weather signals to generate the week-41 statistical baseline for the item-location.
Why it matters: The planner starts from a reproducible baseline with source reliability visible instead of rebuilding the forecast manually.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/statistical-baseline-generation
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Apply approved promotion lifts and net overlapping events so feature-and-display and digital coupon effects are not double counted.
Why it matters: The adjusted forecast reflects incremental demand without stacking overlapping promotion assumptions.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/promotion-and-event-netting
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Compare the adjusted forecast with orders, weather, and prior planning narratives; raise an exception and draft a cited override rationale.
Why it matters: The planner can explain why demand changed and distinguish evidence-backed adjustments from unsupported intuition.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/exception-detection-and-explanation
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Human approval required
What happens: Present the proposed override and cited evidence to planning, sales, and marketing for a named human decision.
Why it matters: Commercial assumptions are challenged and approved before they become an executable demand commitment.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/consensus-review-with-commercial-teams
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Human approval required
What happens: Lock the approved consensus forecast and hand the frozen version to supply planning and procurement.
Why it matters: Operations executes against one auditable forecast version with the override rationale and approvers preserved.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/consensus-lock-and-supply-handoff
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 PlanningUnitForecast evidence.
Select a starter question or enter your own.
Loaded live from /api/config, /api/domain/model, and
/api/domain/sample.
planningUnitForecasts/tenantId + /planningUnitIdA 12-ounce ready-to-drink coffee SKU shipping from the Ohio plant has a 10,000-unit reference forecast. The statistical forecast engine produces 13,400 units for week 41, so (13,400 - 10,000) / 10,000 yields a 34 percent increase; GenAI does not calculate this baseline. The raw uplift contains 19 points from an approved retailer feature-and-display promotion, 11 points from an overlapping digital coupon, and 4 points from warm-weather demand. A deterministic overlap rule nets the coupon from 11 points to 4, removing 700 units and producing a 12,700-unit, 27 percent rules-adjusted forecast. GenAI retrieves the prior consensus minutes and weather advisory, then drafts a cited explanation and override rationale. The planner applies a one-point uncertainty adjustment, approves 12,600 units, a 26 percent increase, records accountability, and locks the consensus version for supply planning and procurement.
| Container | Role | Hierarchical partition key | Document types |
|---|---|---|---|
planningUnitForecasts |
Primary | /tenantId + /planningUnitId |
PlanningUnit, ForecastVersion, PromotionPlan, DemandSignal, PlanningNarrativeChunk, ForecastOverride |
| Type | Container | Partition key | Identifier pattern | Embedding fields |
|---|---|---|---|---|
PlanningUnit |
planningUnitForecasts |
/tenantId + /planningUnitId |
planningUnit::{planningUnitId} |
None |
ForecastVersion |
planningUnitForecasts |
/tenantId + /planningUnitId |
planningUnit::{planningUnitId}::forecast::{versionLabel}::{bucketStartUtc} |
None |
PromotionPlan |
planningUnitForecasts |
/tenantId + /planningUnitId |
planningUnit::{planningUnitId}::promotion::{promotionId} |
None |
DemandSignal |
planningUnitForecasts |
/tenantId + /planningUnitId |
planningUnit::{planningUnitId}::signal::{signalTimestampUtc}::{signalType} |
None |
PlanningNarrativeChunk |
planningUnitForecasts |
/tenantId + /planningUnitId |
planningUnit::{planningUnitId}::narrative::{narrativeDocId}::{chunkOrdinal} |
chunkVector |
ForecastOverride |
planningUnitForecasts |
/tenantId + /planningUnitId |
planningUnit::{planningUnitId}::override::{overrideId} |
rationaleVector |
Evaluate whether one item-location planning unit exceeds the forecast-error review threshold for this cycle. The complete tenantId and planningUnitId hierarchical partition key routes the query to one logical partition.
planningUnitForecasts
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.planningUnitId = @planningUnitId AND c.type = 'PlanningUnit' AND c.categoryCode = @categoryCode AND c.forecastAccuracyMape >= @mapeThreshold ORDER BY c.forecastAccuracyMape DESC
Compare statistical, promotion-adjusted and consensus versions across buckets for one planning unit.
planningUnitForecasts
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.planningUnitId = @planningUnitId AND c.type = 'ForecastVersion' AND c.bucketStartUtc BETWEEN @horizonStartUtc AND @horizonEndUtc ORDER BY c.bucketStartUtc ASC
Detect promotions whose windows overlap so their lifts are netted rather than additively stacked.
planningUnitForecasts
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.planningUnitId = @planningUnitId AND c.type = 'PromotionPlan' AND c.approvalState = 'approved' AND c.endDateUtc >= @horizonStartUtc AND c.startDateUtc <= @horizonEndUtc ORDER BY c.startDateUtc ASC
Retrieve prior consensus minutes and advisories that support or contradict a proposed override.
planningUnitForecasts
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.planningUnitId = @planningUnitId AND c.type = 'PlanningNarrativeChunk' AND c.categoryCode = @categoryCode ORDER BY RANK RRF(VectorDistance(c.chunkVector, @queryVector), FullTextScore(c.chunkText, @queryTerms))