BrazilEnergy and utilities2026 – ongoingIpiranga
Multi-agent AI for pricing, portfolio and fuel supply analysis
Ipiranga cut pricing analysis from 6 hours to 2 hours per consultant with multi-agent AI on Databricks
Problem
Ipiranga is a Brazilian fuel company. Its teams spent long hours on analysis for pricing, portfolio management and fuel supply decisions.
Approach
Ipiranga deployed Databricks Genie with multi-agent AI on a unified data platform. It also used Agent Bricks, Lakebase and Databricks Apps. The AI was applied to daily operations in pricing, portfolio management and fuel supply, and the unified data was used to train and retrain models.
Results
Takeaway
The largest reported time saving was in sales, where the company counted more than 23,000 hours a year. The company did not say how it measured the savings.
Categories
- Size
- Large enterprise
- Industry
- Energy and utilities
- Business function
- Production and qualityMarketing and sales
- Innovation type
- Process innovation
- AI technology
- AI agentsGenerative AI
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Vendor case study
Sources
Source summaries
Databricks describes how Ipiranga, a Brazilian energy company, used Genie and multi-agent AI for pricing, portfolio management and fuel supply. It reports 1,440 hours a year saved in analysis, more than 23,000 hours a year saved in sales, and pricing analysis per consultant down from 6 hours to 2 hours.
Full details are in the original sources.
