Real-time Analytics
IRC teams needed to analyze frontline health data quickly enough to influence staffing, outreach, and supplies, but the information came from ministry-run facilities in inconsistent paper and Excel formats and often had to be used in low-connectivity environments.
Reported impact
IRC reduced management-ready analysis from a full working day to under 30 minutes, saved every surveyed pilot user time, and used the dashboards to validate youth outreach, uncover prenatal-care gaps, and catch infection trends early enough to adjust staffing and supplies.
IRC used Claude Enterprise to create a lightweight offline analytics workflow instead of trying to standardize every upstream data source. In Burkina Faso, staff compile aggregate facility data into Excel and drag those files into a single HTML dashboard template generated and refined with Claude. The template covers more than 15 core health and reproductive-health indicators, runs locally without coding or internet connectivity, and keeps data off Claude's servers. Because the dashboard is just one portable HTML file, measurement specialists and health teams can adapt it in natural language instead of waiting for engineers. The same locally loaded data then supports cross-facility trend analysis, portfolio-level synthesis, and investigations into service gaps, outreach effects, or emerging infection spikes.
Facility data moves from paper registers or DHIS-2 into local Excel files, staff drag those files into an HTML dashboard template generated with Claude, and the offline output surfaces indicator trends and anomalies for health teams to discuss and act on locally.
A drag-and-drop workflow where staff load facility Excel files locally, no connectivity or coding required
Across three health facilities, the dashboard flagged STI consultations among people under 18 jumping from an average of 21 per month to 88
No connectivity or coding is required, and the data is not sent externally or stored on Claude’s servers.
Offline HTML dashboards covering more than 15 core health and reproductive health indicators
One program user now prepares analysis and slides for senior management in under 30 minutes, work that previously took a full day.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Anthropic Sample Archived · Sep 28, 2026 International Rescue Committee IRC wanted proof that AI could turn inconsistent frontline health data into useful local decision support despite electricity constraints, poor connectivity, and ministry-defined indicators that varied across facilities. 2,700+ health facilities across 40 countries Claude Enterprise Anthropic Sample Archived · Sep 23, 2026 Supermetrics Marketers and agencies had no shortage of dashboards, but still had to manually export, reconcile, and report data from multiple ad platforms, making campaign analysis slow and too risky for AI systems that hallucinate. 10-hour reports done in 20 minutes Claude Code · Claude Cowork · Google Cloud's Agent Platform 
Google Cloud Sample Archived · Sep 17, 2026 IATA IATA wanted a repeatable short-term air-travel forecasting signal to complement long-term econometric models, but needed the entire workflow to run automatically each month with richer features and no manual… One global ML model produces approximately 5,700 bidirectional forecasts Cloud KMS · Cloud Run functions · Cloud Scheduler 