Normalized claim
Senior leaders with access: 100 leaders
“About 100 senior leaders already have access to the agent, called LUCA Bot.”
MicrosoftEvidence: Medium50/100
Cemex: LUCA Bot AI agent for executive financial insights
Use case typeExecutive analyticsUpdated Feb 12, 2026
Cemex built LUCA Bot in Microsoft Foundry with Azure OpenAI, Azure AI Search, Azure Cosmos DB, Azure App Service, Microsoft Teams and Azure Storage to give executives natural-language access to internal financial and economic KPIs across regions, countries and plants. The agent was trained on thousands of internal data points and more than 35,000 questions, supports role-based access, and helps senior leaders get faster, more reliable answers for decision-making.
- Organization
- Cemex
- Industry
- Manufacturing
- Location
- Mexico
- Published
- February 2026
Reported outcomes
400-500 queries/month
queries per monthOther quantified impact
100 leaderssenior leaders with access82%analysis accuracy92%data accuracy
Strategic outcomes
Better decisions & insightFaster executive decision-makingCost efficiencySelf-service access to unified financial informationBetter decisions & insightSupports quarterly executive committee presentationsOther strategic outcomePotential expansion from executives to lower management and employees
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Queries per month: 400-500 queries/month
“Today, LUCA Bot is handling 400 to 500 queries per month”
Normalized claim
Analysis accuracy: 82%
“with 82% accuracy for analysis”
Normalized claim
Data accuracy: 92%
“and 92% for data”
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Cemex
- Provider
- Microsoft
- Maturity
- Unknown
- Linked source
- Microsoft Source
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 3
- 1Executive analytics
- 2Search modernization
- 3Employee productivity
- Executives previously spent hours or days searching reports, emails and phone calls to find internal financial KPIs and analysis.
- Cemex needed a faster, reliable way to access granular financial data across multiple regions and plants.
- LUCA Bot is an executive-focused AI agent that responds in natural language through web and mobile channels and delivers KPI analysis based on internal financial and economic data.
- The system uses Microsoft Foundry, Azure OpenAI and Azure AI Search to support prompt-driven interaction, role-based access and daily updates from executive feedback.
- About 100 senior leaders have access to the agent.
- The agent handles 400 to 500 queries per month.
- Cemex reports 82% accuracy for analysis and 92% for data.
Architecture
Built in Microsoft Foundry with Azure OpenAI models and wired to Azure AI Search, Azure Cosmos DB, Azure App Service, Microsoft Teams and Azure Storage. The agent uses role-based access, prompt and instruction engineering, and draws on thousands of internal confidential financial and economic data points plus a trained set of more than 35,000 questions. It serves authorized executives through natural-language chat on web and mobile, with only basic session data retained in the Azure tenant.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Feb 12, 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
AI patterns
Browse the catalog
Was this useful?
Community
Comments
Loading comments...