Real-time Analytics
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.
Reported impact
The Burkina Faso pilot showed that IRC teams could create dashboards in about 20 minutes, adapt them without engineers, and give nearly 3,000 facilities facing similar constraints a repeatable way to turn local data into faster program decisions.
The IRC Q&A describes the Burkina Faso pilot as a deliberately simple, chat-built analytics system on Claude Enterprise. Rather than redesigning upstream collection, the team focused on one variable: visualization. Measurement specialists and health teams use Claude to create and revise an HTML dashboard template around the indicators they already track, then send the lightweight file to facilities where local Excel data can be dropped in with no internet connection. The team explicitly notes that they did this in chat, without Claude Code, which made it practical for non-engineers to adapt the dashboards themselves. That combination of local files, natural-language customization, and repeated facility-level use turned a previously manual reporting process into a reusable pattern that can scale across thousands of sub-Saharan health facilities facing the same data problem.
Facility staff enter aggregate figures into paper registers and Excel, IRC teams use Claude to build an HTML dashboard template, and each site loads its local Excel file into the template to produce charts and summaries offline for local health discussions.
20 minutes to create HTML dashboards in Claude
It’s close to 23,000 healthcare facilities in sub-Saharan Africa that have the same problem.
Then they can take their Excel file from that local facility and just drag and drop it in there. No connectivity needed.
We just did it in the chat. We didn’t even need Claude Code
When you consider that nearly 3,000 health facilities across sub-Saharan Africa face the same data challenge, what works in Burkina Faso has the potential to change how health teams across the region use data.
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 · Oct 4, 2026 International Rescue Committee 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… 4+ hours per month saved by half of surveyed pilot users 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 