Decision owner
Content executive and analytics lead
The named role remains accountable for the consequential decision.
Media, Entertainment & Gaming
Designed for Content executive
Give content executives a defensible narrative of how a title or franchise is performing by linking engagement, cohort behaviour, campaign spend, and social signal into cited explanations that drive slate and marketing decisions.
Contract MED-03 · primary aggregate AudienceNarrative · 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
Content executive and analytics lead
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 drama series holds strong opening viewership but loses 28 percent completion on mobile in week three; the narrator links the drop to a cohort acquired through a discount campaign, shows organic cohorts completing at benchmark, notes a social theme complaining about episode pacing, and the executive approves the narrative ahead of the renewal discussion..
Give content executives a defensible narrative of how a title or franchise is performing by linking engagement, cohort behaviour, campaign spend, and social signal into cited explanations that drive slate and marketing decisions.
Approved narrative informing renewal or marketing decisions gives Content executive and analytics lead 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.
Content executive and analytics lead 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: Content executive performs select the title and reporting period using Title or franchise and period of interest and produces AudienceNarrative shell with decision questions. The transition is deterministic and does not require autonomous model approval.
Why it matters: AudienceNarrative shell with decision questions gives Metrics assembly service the evidence needed to begin Assemble engagement and cohort rollups, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/select-the-title-and-reporting-period
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Metrics assembly service performs assemble engagement and cohort rollups using Pre-aggregated engagement and cohort profiles and produces Metric pack scoped to the period. The transition is deterministic and does not require autonomous model approval.
Why it matters: Metric pack scoped to the period gives Attribution agent the evidence needed to begin Separate marketing effect from organic demand, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/assemble-engagement-and-cohort-rollups
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Attribution agent performs separate marketing effect from organic demand using Campaign flights and start curves and produces Attributed versus organic breakdown. The transition is deterministic and does not require autonomous model approval.
Why it matters: Attributed versus organic breakdown gives Narrative agent the evidence needed to begin Draft the explanatory narrative, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/separate-marketing-effect-from-organic-demand
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Narrative agent performs draft the explanatory narrative using Metric pack, attribution, and social themes and produces Cited narrative with confidence and caveats. The transition is deterministic and does not require autonomous model approval.
Why it matters: Cited narrative with confidence and caveats gives Content executive and analytics lead the evidence needed to begin Executive review before slate decisions, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/draft-the-explanatory-narrative
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Human approval required
What happens: Content executive and analytics lead performs executive review before slate decisions using Draft narrative with cited metrics and produces Approved narrative informing renewal or marketing decisions. A named human approver must review the evidence before the transition completes.
Why it matters: Approved narrative informing renewal or marketing decisions gives Content executive and analytics lead 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/executive-review-before-slate-decisions
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 AudienceNarrative evidence.
Select a starter question or enter your own.
Loaded live from /api/config, /api/domain/model, and
/api/domain/sample.
audienceNarratives/tenantId + /titleFranchiseIdA drama series holds strong opening viewership but loses 28 percent completion on mobile in week three; the narrator links the drop to a cohort acquired through a discount campaign, shows organic cohorts completing at benchmark, notes a social theme complaining about episode pacing, and the executive approves the narrative ahead of the renewal discussion.
| Container | Role | Hierarchical partition key | Document types |
|---|---|---|---|
audienceNarratives |
Primary | /tenantId + /titleFranchiseId |
AudienceNarrative, EngagementMetricRollup, CohortBehaviourProfile, CampaignPerformanceRecord, SocialSignalDigest |
| Type | Container | Partition key | Identifier pattern | Embedding fields |
|---|---|---|---|---|
AudienceNarrative |
audienceNarratives |
/tenantId + /titleFranchiseId |
narrative::{titleFranchiseId}::{periodLabel} |
narrativeVector |
EngagementMetricRollup |
audienceNarratives |
/tenantId + /titleFranchiseId |
engagement::{titleFranchiseId}::{periodLabel}::{platformCode} |
None |
CohortBehaviourProfile |
audienceNarratives |
/tenantId + /titleFranchiseId |
cohort::{titleFranchiseId}::{cohortId} |
None |
CampaignPerformanceRecord |
audienceNarratives |
/tenantId + /titleFranchiseId |
campaign::{titleFranchiseId}::{campaignId} |
None |
SocialSignalDigest |
audienceNarratives |
/tenantId + /titleFranchiseId |
social::{titleFranchiseId}::{digestDate} |
themeVector |
Read engagement, cohort, and campaign records for the title and period in one partition query.
audienceNarratives
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.titleFranchiseId = @titleFranchiseId AND c.type IN ('EngagementMetricRollup','CohortBehaviourProfile','CampaignPerformanceRecord') AND c.periodLabel = @periodLabel ORDER BY c.uniqueViewers DESC
Find platforms where completion collapsed against the franchise benchmark.
audienceNarratives
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.titleFranchiseId = @titleFranchiseId AND c.type = 'EngagementMetricRollup' AND c.completionRate < @benchmarkCompletionRate ORDER BY c.completionRate ASC
Rank campaign flights by attributed starts per unit of spend.
audienceNarratives
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.titleFranchiseId = @titleFranchiseId AND c.type = 'CampaignPerformanceRecord' AND c.flightEndUtc <= @periodEndUtc ORDER BY c.attributedStarts DESC
Detect days where social volume spiked with negative sentiment.
audienceNarratives
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.titleFranchiseId = @titleFranchiseId AND c.type = 'SocialSignalDigest' AND c.volumeCount > @volumeThreshold ORDER BY c.digestDate DESC