← All case studies
Healthcare · AI agents

Conversational insights on governed data for a pharmaceutical manufacturer

A leading pharmaceutical manufacturer

65%of routine KPI questions self-served by digests and the agent
65%

Of routine KPI questions self-served

Days → minutes

To a trusted answer

90%

Lower cost per question on cached context

The challenge

Commercial reporting existed, but insight reached leadership only when someone opened or built a dashboard. KPI monitoring was reactive, sales-force effectiveness data sat apart from commercial and market data, metric definitions drifted between teams and spreadsheets, and business users depended on analysts to translate questions that mixed English and Urdu.

What we built
  • A governed semantic layer in Tableau Cloud over SAP Business Data Cloud, so every number has one certified definition.
  • Tableau Pulse sends commercial, sales-force and market KPI digests to leaders by subscription instead of dashboard-only access.
  • A conversational agent, built with Tableau MCP, LangGraph and Claude, queries the published Tableau source rather than the warehouse, so it inherits the certified definitions and stays aligned with the dashboards.
  • Restricted metrics isolated by audience and mandatory business filters encoded in the agent contract, with separate agents for internal sales and market data.
  • Mixed English and Urdu business vocabulary supported.
The results
  • 65% of routine KPI questions are self-served by digests and the agent before they reach the reporting team.
  • A multi-day report cycle became one governed conversational exchange.
  • Prompt caching and iteration caps cut the cost per question by 90%, keeping it sustainable.
Similar challenge?

Let's talk about what this could look like in your business.