Normalized claim
Interactions per engaged session: 3 count increase
visitors who engage with the agent are averaging about three interactions per session
MicrosoftEvidence: Medium50/100
The Ad Council: Copilot Studio AI agent with Azure AI Search for Youth Firearm Injury Prevention
Use case typeCustomer service agentUpdated Jun 13, 2026
The Ad Council built an AI-powered chat experience for its Youth Firearm Injury Prevention campaign, Agree to Agree. The solution uses Microsoft Copilot Studio as the conversational layer and Azure AI Search with Azure OpenAI, Azure Blob Storage, Azure Functions, and Power Automate to ground responses in vetted campaign resources. The agent is designed to guide users toward trusted, approved information while avoiding harmful, political, or crisis-escalation content.
- Organization
- The Ad Council
- Industry
- Public Sector
- Location
- United States
- Published
- June 2026
Reported outcomes
3 count
interactions per engaged sessionOther quantified impact
Strategic outcomes
Customer experience & trustImproved engagement with vetted campaign resourcesRisk & complianceGrounded responses in approved materials with guardrailsOther strategic outcomeRedirected harmful or crisis prompts to support resources
Why do we believe this?Outcome claims, sources, and evidence checks
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- The Ad Council
- Provider
- Microsoft
- Maturity
- Unknown
- Linked source
- Microsoft Customer Story
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 3
- 1Customer service agent
- 2Content discovery assistant
- 3Workflow automation
- Parents and other concerned adults needed help navigating hard, sensitive questions about firearms and child safety.
- The campaign needed a controlled experience that would reduce barriers while operating within strict legal, ethical, and safety boundaries.
- Users needed an approachable way to engage trusted resources without drifting into harmful or divisive content.
- The Ad Council used Microsoft Copilot Studio to build a controlled conversational agent with custom topics and workflows.
- The team built a curated knowledge base of approved campaign pages in Azure Blob Storage and indexed it with Azure AI Search using Azure Functions and Azure OpenAI embeddings.
- Power Automate connects Copilot Studio topics to backend automation and data retrieval, while trigger-word detection redirects crisis or harmful prompts to support resources.
- Visitors who engage with the agent average about three interactions per session.
- The conversational experience increases engagement with vetted campaign content and supports safer conversations about firearms.
- The organization can update approved resources without rebuilding the entire experience.
Architecture
The Ad Council's solution uses Microsoft Copilot Studio for the agent experience, Azure Blob Storage and Azure Functions for controlled ingestion, Azure AI Search for retrieval, Azure OpenAI for embeddings, and Power Automate as the workflow layer. The architecture keeps the model grounded in vetted campaign content and adds trigger-word handling to redirect unsafe prompts.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Jun 13, 2026Publisher: MicrosoftEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Market context
Browse the catalog
Was this useful?
Community
Comments
Loading comments...