---
title: "How Ecolab rebuilt retail intelligence on Databricks and Anthropic Claude"
description: "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."
---

# How Ecolab rebuilt retail intelligence on Databricks and Anthropic Claude

[Databricks](https://yomu.fyi/company/databricks) · Babu Chinnaswamy, Nicholas Dylla, Alissa Ellingson, Harish Gaur · Jun 11, 2026

**Type:** Problem & solution

## 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.

## Context

Ecolab's food safety, pest control, and water quality data was distributed across nine systems. Managers could spend hours searching a 700-page FDA food code, and compiling a compliance report for one location could take two weeks.

## Approach / What changed

Ecolab built a native Databricks App with Lakebase Postgres, Lakeflow, Spark Declarative Pipelines, and Unity Catalog. A multi-agent supervisor architecture combines specialized retrieval and data-query agents with Claude models, dual-layer memory, governance controls, evaluation, tracing, and batch inference.

## Takeaways

- 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.
- 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.
- 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.

**Tags:** [Databricks](https://yomu.fyi/topic/databricks), [Lakebase](https://yomu.fyi/topic/lakebase), [Lakehouse](https://yomu.fyi/topic/lakehouse), [LLMs](https://yomu.fyi/topic/llm), [MCP](https://yomu.fyi/topic/mcp)

- Source: [Databricks](https://www.databricks.com/blog/how-ecolab-rebuilt-retail-intelligence-databricks-and-anthropic-claude)
- Source URL: https://www.databricks.com/blog/how-ecolab-rebuilt-retail-intelligence-databricks-and-anthropic-claude
- Ingested by Yomu: 2026-08-30T17:03:26.295Z

[Read original post](https://www.databricks.com/blog/how-ecolab-rebuilt-retail-intelligence-databricks-and-anthropic-claude)