Enterprise Knowledge Search
Users and stakeholders needed a quicker, easier way to access official information and data across eni.com without relying on manual search or traditional browsing.
Reported impact
EnergIA gives users faster, more goal-oriented access to official Eni information, provides richer responses with cited sources, and is intended to improve accessibility, transparency, and understanding of the company.
Eni built EnergIA as a first-party generative AI experience on eni.com to help users and stakeholders find official company information faster. The user submits a natural-language question in Italian, English, or another language through EnergIA, which routes retrieval against the appropriate site language corpus. Behind the interface, Large Language Models analyze Eni’s official content and use Retrieve Augmented Generation (RAG) to pull the most relevant material from a knowledge base made up of webpages, financial documents from the previous twelve months, press releases from the previous two years, and selected strategic documents. The system automatically incorporates newly published website content almost in real time, keeps temporary conversational memory so follow-up questions can use prior context, and returns natural-language answers with cited official sources and direct links back to the relevant Eni or group-company pages.
A user asks a question in EnergIA; the system selects the relevant Italian or English content set on eni.com, uses RAG to retrieve matching webpages and documents from its knowledge base, has Large Language Models generate a response from those official sources, and returns the answer with source links while keeping session history until inactivity clears it.
"A window on Eni’s world, updated in real time. The system automatically integrates new content, almost as soon as it is published on the website."
"EnergIA uses this technology, specifically ‘Large Language Models’, to analyse the information available on eni.com and generate responses based on official sources."
"EnergIA" tool is based on generative artificial intelligence and helps users to rapidly locate information on eni.com.
"Faster than a manual search or traditional browsing"
"Richer responses with a list of sources directing you to more details"
"The sources used by EnergIA include the most relevant content available on eni.com: webpages, financial documents from the past twelve months, press releases from the past two years, and a selection of documents deemed strategic for the project."
"The system uses the Retrieve Augmented Generation (RAG) method to find the most pertinent content in its knowledge base when answering a user’s question."
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
In-house Sample Oct 15, 2025 Repsol Repsol wanted to help employees reinvent workflows, improve working models, and raise productivity in complex internal processes as part of its broader digitalization program. 22 of which have already been scaled up innovative interface · intelligent agent construction platform · language models In-house Sample Oct 17, 2024 OMV OMV needs to reduce uncertainty in complex geothermal and carbon capture and storage decisions, while also making large volumes of structured and unstructured subsurface data easier for geoscientists to find, summarize,… AI-driven decision-making tool · OMV Energy Chat Bot · knowledge graphs 
NVIDIA Sample Sep 30, 2026 EPRI EPRI needed to run advanced AI for sensitive utility documents and weather-planning workflows locally, because energy-sector research data could not leave controlled environments and shared compute delays limited how… 150 tokens/sec aggregate across 10 concurrent Power Chat users DGX Spark · Dell Pro Max with GB10 · NVIDIA CBottle 