EnergyGenerative AIPublic CloudDatabricks Data + AI PlatformDatabricks Lakeflow JobsGPT-4oMistral OCRDatabricks Model Serving

Axpo boosts operational efficiency across the energy value chain

Axpo Group · Switzerland

Axpo Group, a major player in the Swiss energy sector, built a GenAI knowledge platform on the Databricks Data + AI Platform to give employees secure, permission-aware search across internal data sources including technical standards, specifications and best practices. The architecture uses a medallion pattern (Bronze/Silver/Gold layers), Lakeflow Jobs for orchestration, RAG-based AI Search, GPT-4o for conversational responses, and Mistral OCR for scanned documents. The tool achieved a 90% approval rating and delivered 30% time savings for power users, with a 3x increase in user adoption as it expanded beyond engineering.

Overview

Axpo Group, a major player in the Swiss energy sector, built a GenAI knowledge platform on the Databricks Data + AI Platform to give employees secure, permission-aware search across internal data sources including technical standards, specifications and best practices. The architecture uses a medallion pattern (Bronze/Silver/Gold layers), Lakeflow Jobs for orchestration, RAG-based AI Search, GPT-4o for conversational responses, and Mistral OCR for scanned documents. The tool achieved a 90% approval rating and delivered 30% time savings for power users, with a 3x increase in user adoption as it expanded beyond engineering.

This entry has 14 published fields tied to exact passages in an immutable source capture.

Inspect the highlighted source

The challenge

Axpo's engineers and other employees needed a faster way to access critical internal knowledge such as technical standards, specifications and best practices, but legacy challenges — data silos, fragmented tools and manual processes — slowed progress. Critical knowledge was scattered across siloed systems, forcing employees to rely on point-of-contact subject matter experts, and disconnected tools and workflows hindered collaboration between data engineering and ML teams. Growing concerns around data residency and governance underscored the need for a centralized, compliant platform.

The solution

Axpo's Generative AI Competence Center built a GenAI knowledge assistant on the Databricks Data + AI Platform, following a medallion architecture (Bronze/Silver/Gold layers) with raw data from sources like Confluence wikis. Lakeflow Jobs orchestrate daily pipelines to index and enrich content. A RAG-based AI Search index over the Gold layer enables secure, permission-aware retrieval enforced with row-level access controls, OpenAI's GPT-4o generates conversational responses, and Mistral's OCR model extracts searchable content from scanned PDFs and attachments. The agent is deployed via Databricks Model Serving as an endpoint integrated into internal dashboards, chat tools and the Axpo Insights product. Machine learning is also used to automatically classify vendor and spending data for procurement visibility.

Generative AIRetrieval-Augmented GenerationConversational AIDocument Intelligence

Reported business value

Internal users report over 90% satisfaction (approval rating) with the knowledge assistant. Project managers and other power users estimate they've reclaimed up to 30% of their time. Adoption has grown 3x as the tool expanded beyond its original engineering audience company-wide.

Related entries

Other energy entries in the register.

All entries
EnergyNatural Language ProcessingPublic Cloud

Building a clean energy future with natural language analytics

Williams, a large-scale natural gas infrastructure operator, deployed Databricks AI/BI Genie to give commercial, regulatory, accounting and technical staff natural-language, self-serve access to analytics. The team flattened 27 disparate tables into SQL models that Genie Spaces reason over, encoding internal acronyms and business logic into Genie's instructions, powered by Databricks Unity Catalog. A data request that previously took an analyst five days now completes in seconds with validated accuracy, and the weekly backlog of data requests dropped from up to ten to one or two, freeing analysts for predictive modeling and enterprise projects.

96/100HighWilliamsPrimary source
EnergyPredictive AnalyticsPublic Cloud

Plenitude builds machine learning models on Databricks to forecast energy demand and renewable production

Eni-owned energy company Plenitude, which serves 10 million households and businesses across Europe, uses statistical models and machine learning on the Databricks Data + AI Platform to forecast customer energy consumption at hourly and daily granularity, forecast wind and solar generation from its renewable asset portfolio, and run customer segmentation and propensity models across 60 implemented use cases.

100/100HighPlenitudePrimary source
EnergyPredictive AnalyticsUnknown

TotalEnergies builds Pangea 5 supercomputer with Dell Technologies and NVIDIA

TotalEnergies is building Pangea 5, a next-generation supercomputer developed with Dell Technologies and NVIDIA that will increase the company's computing power to support seismic imaging, advanced simulation and AI-driven research in the energy sector.

92/100HighTotalEnergiesPrimary source
EnergyNatural Language ProcessingPublic Cloud

AES accelerates renewable energy adoption with Claude on Google Cloud

AES, a global energy company, built a multi-agent AI system using Claude on Google Cloud to automate internal safety audits of its renewable energy assets. The system uses document processing agents, task breakdown agents, and report generation agents to process hundreds of pages of safety documentation, evaluate compliance, and produce audit reports. Audit reports that previously took up to two weeks to complete (across roughly 1,550 internal audits annually) can now be generated in about an hour, a 99% reduction in time, alongside a 10-20% improvement in audit accuracy and a 99% reduction in audit costs.

96/100HighAESPrimary source

Was this helpful?

Your feedback helps us improve our use case database