How Ecolab rebuilt retail intelligence on Databricks and Anthropic Claude

Summary

Ecolab needed to combine audits, health inspections, pest telemetry, and other data from nine systems so retail teams could answer location-specific compliance questions. Its Retail Intelligence application is a native Databricks App using Lakebase Postgres, Lakeflow, and Spark Declarative Pipelines to move governed data into a Unity Catalog lakehouse, while Foundation Model APIs serve Claude Sonnet, Claude Haiku, and Gemini. A Coordinator Agent delegates requests to specialized agents that use Vector Search, SQL, Unity Catalog Functions, and an external MCP server; a Response Agent returns cited answers, with short- and long-term memory stored through Lakebase. The system also applies five Judge LLMs, MLflow tracing, and ai_query() batch inference. Report preparation fell from two weeks to under two minutes, while the assistant supports approximately twelve languages at about 98% accuracy.

Takeaways

1. 1

   The Coordinator Agent delegates questions to specialized agents using Vector Search, SQL and Unity Catalog Functions, or an external MCP server, then a Response Agent assembles a cited answer.

2. 2

   Claude Sonnet handles complex reasoning and long-term user memory, while Claude Haiku summarizes conversation history and data signals for faster, lower-cost interactions; Gemini performs image analysis.

3. 3

   Compliance report preparation decreased from two weeks to under two minutes, and FDA food-code answers that previously required hours of PDF searching return in seconds.