Skip to main content
MED-03 · Media, Entertainment & Gaming

Audience Insight Narrator

Outcome​

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.

Portfolio attributeValue
Primary personaContent executive
Primary aggregateAudienceNarrative
Cosmos DB containers1
Grounding dataengagement, cohorts, campaigns, social signals
Development estimateUSD 60-220 monthly dev estimate
Runtime optionsPython FastAPI and C# ASP.NET Core

Productivity hypothesis​

These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.

Impact typeMeasureConservative internal assumptionCustomer measurement
ProductivityExecutive analysis cycle time8-16% reduction(baseline median analysis minutes - assisted median analysis minutes) / baseline median analysis minutes * 100
Quality or riskEvidence discovery time10-20% reduction(baseline median evidence-search minutes - assisted median evidence-search minutes) / baseline median evidence-search minutes * 100

Important: Conservative internal pilot assumptions only; not public benchmarks, commitments, or expected customer results. Validate against a comparable baseline or matched control cohort with mandatory human review.

Rationale: Playback, campaign, social, game, and release evidence can be reconciled faster into decision-ready narratives.

Pilot guardrail: Cite executive claims and expose conflicting evidence and attribution limitations.

Customer validation plan​

  1. Baseline the current workflow with representative users and tasks.
  2. Run the accelerator on the same task mix with human review retained.
  3. Measure executive analysis cycle time and evidence discovery time with the documented formulas.
  4. Replace internal assumptions with customer-observed results before a business case.

Why Azure Cosmos DB​

This AI solution needs an operational data plane, not only a vector index:

  • Hybrid vector and full-text retrieval combines semantic recall with exact identifiers, codes, names, and domain language.
  • Hierarchical partition keys and metadata predicates keep tenant and domain boundaries in the normal query path.
  • Operational JSON, source chunks, workflow and agent state, feedback, and audit records remain together for low-latency reads and governed writes.
  • Change feed reacts to source and operational updates without polling.
  • Autoscale throughput, configurable consistency, and multi-region distribution support variable demand and enterprise availability.

Domain workflow​

Domain workflow

StageActorInput → outputApproval
1. Select the title and reporting periodContent executiveTitle or franchise and period of interest → AudienceNarrative shell with decision questionsPolicy controlled
2. Assemble engagement and cohort rollupsMetrics assembly servicePre-aggregated engagement and cohort profiles → Metric pack scoped to the periodPolicy controlled
3. Separate marketing effect from organic demandAttribution agentCampaign flights and start curves → Attributed versus organic breakdownPolicy controlled
4. Draft the explanatory narrativeNarrative agentMetric pack, attribution, and social themes → Cited narrative with confidence and caveatsPolicy controlled
5. Executive review before slate decisionsContent executive and analytics leadDraft narrative with cited metrics → Approved narrative informing renewal or marketing decisionsHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
audienceNarratives/tenantId, /titleFranchiseIdAudienceNarrative, EngagementMetricRollup, CohortBehaviourProfile, CampaignPerformanceRecord, SocialSignalDigest/narrativeVectorEmbedding, /themeVectorEmbedding, /narrativeVector, /themeVector

Query contract​

QueryContainerScopePurpose
Period performance assemblyaudienceNarrativessingle-partitionRead engagement, cohort, and campaign records for the title and period in one partition query.
Drop-off anomaly detectionaudienceNarrativessingle-partitionFind platforms where completion collapsed against the franchise benchmark.
Campaign efficiency rankingaudienceNarrativessingle-partitionRank campaign flights by attributed starts per unit of spend.
Sentiment shift watchaudienceNarrativessingle-partitionDetect days where social volume spiked with negative sentiment.

Python and C# services route each document type to its declared container and hierarchical partition key. ETag-based writes protect mutable aggregates, while append-only records and bounded cross-partition queries preserve scale.

Azure deployment​

Azure deployment

Clone the source repository, authenticate with Azure, and run:

Set-Location accelerators/media-entertainment-gaming/audience-insight-narrator
az login
./Deploy.ps1 -Runtime python -Location eastus2

Change python to csharp to deploy the .NET implementation.

Explore the implementation​

Return to all accelerators