Document Processing · Enterprise Knowledge Search
Eni needed to make multilingual subsurface documents and extracted scientific data usable across geoscience teams, but its relational platform struggled with hundreds of thousands of documents, terabytes of unstructured content, and the complexity of creating comprehensive, searchable datasets for global research and drilling decisions.
Reported impact
Eni improved platform performance and manageability, reduced development time and associated costs, gave scientists faster access to comprehensive subsurface datasets, and created a cloud-agnostic document platform that can support broader enterprise rollout and future generative-AI enhancements.
Eni rebuilt its geoscience document platform on MongoDB Atlas with support from MongoDB Consulting. The new managed document data platform ingests processed text, tables, images, metadata, and AI-enriched outputs from subsurface documents, then exposes that information through search, dashboards, and custom applications used by geologists, engineers, and drilling teams. Atlas Search helps users filter relevant documents across years and geographies, while Atlas Charts gives non-developers a code-free way to visualize unstructured data in dashboards instead of exporting CSVs and spreadsheets. Atlas fits Eni's multi-cloud strategy and simplifies security, encryption, deduplication, scaling, and routine maintenance. The result is a shared knowledge environment that shortens development work, improves data completeness for research decisions, and provides the document foundation for NLP and generative-AI services that answer questions with grounded scientific context.
Geoscience documents are extracted and enriched with AI, stored in Atlas as text, tables, images, and metadata, surfaced through Search and Charts for specialists and analysts, and fed into NLP and generative-AI services that retrieve relevant documents before answering questions.
Atlas Charts is really useful to visualize unstructured data.
Eni’s document management platform for geosciences offers an ecosystem of services and applications for creating and sharing content.
MongoDB Atlas is simple to integrate and makes it easy to ingest and deduplicate data from other systems.
The generative AI we’ve introduced currently creates vector embeddings from documents, so when a user asks a question, it retrieves the most relevant document and uses LLMs to build the answer.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
MongoDB Sample Oct 8, 2026 Navisio AI Rapid adoption of Navisio AI's platform triggered severe latency spikes, elevated CPU and RAM consumption, and costly vertical scaling. As it prepares to scale to 1,000 by the end of the year, and eventually toward 5,000 users, the team is… MongoDB Atlas · MongoDB Atlas Vector Search MongoDB Sample Sep 9, 2026 Squary AI Squary AI needed to eliminate slow, outage-prone legal search infrastructure that combined MongoDB with OpenSearch and hurt document review speed, cost, and trust. At Quatrini Law Group, Squary AI analyzed more than 460,000 pages and saved over 400 attorney and paralegal hours. Amazon Bedrock · Claude · MongoDB Atlas 
Deutsche Telekom Sample Apr 14, 2026 Thüga AG Public utilities in Thüga's network manage sensitive data from network operations, customer management, and regulatory processes, and need a secure way to introduce AI without losing digital sovereignty or forcing each… around 100 public utilities Enterprise GPT solutions · T Cloud Public 