Repsol
Self-service analytics
Most employees couldn't reach the data without an analyst. Refinery experts now build soft sensors through conversation, no code needed.
- 4,000 hours saved annually via Genie Code
Maintenance data spanned 60 systems and 11 spellings of "Gulf of Mexico." Engineers now ask Genie plain-language questions directly.
A global energy company operating offshore production, refining, terminals and pipelines, with maintenance data spread across roughly 60 source systems including 47 SAP instances and Maximo.
Each system used its own terminology, with 11 different ways to spell Gulf of Mexico alone, so maintenance engineers depended on data engineers and...
Global integrated oil and gas company producing energy and fuel products.
Databricks is a Big Data company that offers a unified analytics platform for data science, engineering, and analytics teams.
bp's Maintenance Q&A is part of this use case:
Related implementations across industries and use cases
Most employees couldn't reach the data without an analyst. Refinery experts now build soft sensors through conversation, no code needed.
Crews wasted time verifying safety docs. A GenAI assistant now serves instant, authorized answers, scaling to 4,000 technicians.
Flying blind with agents in critical infrastructure — raw logs the only window. Now production traces feed evaluation before every release.
Siloed data across departments slowed executive decisions. Unified on Databricks with AI agents, pricing and sales now run on data, not instinct.
Staff filed data requests through chat and waited days for analyst replies. Now they ask the data lake directly—no SQL, no queue.
Forecasts that took 10+ hrs on shared CPU clusters now run in 150 sec—giving grid planners time to act, not just react.
No-code tools worked for chatbots, not agents. Coding each from scratch took weeks. Microsoft Foundry cut that to a day.
A decade of tool growth left regional procurement scattered, invisible to the center. One platform, bought not built, surfaced them all.
Multiple staff, one spreadsheet, inconsistent logs. Staff now describe incidents; AI classifies each, improving with every game.
Maintenance data spanned 60 systems and 11 spellings of "Gulf of Mexico." Engineers now ask Genie plain-language questions directly.
A global energy company operating offshore production, refining, terminals and pipelines, with maintenance data spread across roughly 60 source systems including 47 SAP instances and Maximo.
Each system used its own terminology, with 11 different ways to spell Gulf of Mexico alone, so maintenance engineers depended on data engineers and...
Global integrated oil and gas company producing energy and fuel products.
Databricks is a Big Data company that offers a unified analytics platform for data science, engineering, and analytics teams.
bp's Maintenance Q&A is part of this use case:
Related implementations across industries and use cases
Most employees couldn't reach the data without an analyst. Refinery experts now build soft sensors through conversation, no code needed.
Crews wasted time verifying safety docs. A GenAI assistant now serves instant, authorized answers, scaling to 4,000 technicians.
Flying blind with agents in critical infrastructure — raw logs the only window. Now production traces feed evaluation before every release.
Siloed data across departments slowed executive decisions. Unified on Databricks with AI agents, pricing and sales now run on data, not instinct.
Staff filed data requests through chat and waited days for analyst replies. Now they ask the data lake directly—no SQL, no queue.
Forecasts that took 10+ hrs on shared CPU clusters now run in 150 sec—giving grid planners time to act, not just react.
No-code tools worked for chatbots, not agents. Coding each from scratch took weeks. Microsoft Foundry cut that to a day.
A decade of tool growth left regional procurement scattered, invisible to the center. One platform, bought not built, surfaced them all.
Multiple staff, one spreadsheet, inconsistent logs. Staff now describe incidents; AI classifies each, improving with every game.