Veolia Italia

Project Details

Veolia Italia partnered with auticon to build an LLM-based agent that turns unstructured PDF documents into structured, analysis-ready data.

Country:Italy

Industry:Energy & Utilities

Engagement:AI & Machine Learning | Data Services | Generative AI | Software Development

Tech StackGenerative AI framework, LangChain, Large Language Models (LLMs), PDF processing, Python, Streamlit

Showcased how a neurodivergent auticon consultant brought a structured, modular working method that became a best practice within Veolia, while delivering tangible business value through Generative AI.

About

Veolia Italia is a leading provider of efficient energy, water and special-waste management, supporting public and private clients on their decarbonisation journey through integrated energy efficiency measures and local renewable energy production. It manages more than 13,000 buildings (schools, hospitals, public and private properties) and 150 industrial sites each year, and is part of the global Veolia group, a world leader in environmental services.

The Challenge

Veolia’s Italian operators had to manually search for data inside multi-POD energy bills, rebuild tables in Google Sheets, and handle different formats for each supplier. Bills could run to thousands of PDF pages with heterogeneous, non-standardised structures. The goal was to make this data quickly accessible and analysable to support energy audits, technical reports and regulatory reporting in a simple, scalable and replicable way.

The Solution

auticon developed an LLM-based agent that transforms digital PDF documents into structured data. The user uploads one or more documents, defines the fields to extract, and the agent automatically generates an analysis-ready table. The application was built in Python with LangChain, integrated with Streamlit for rapid front-end development, and embedded in a scalable framework for deploying Generative AI applications. Initially built for energy audits, it quickly proved effective on multi-supplier bills, invoices, technical reports and cybersecurity documentation.

The Benefits

Significant reduction in time to extract data from complex documents
Greater standardisation of information across different suppliers
Data immediately usable in Google Sheets, databases and analysis tools
Reusable internal framework for future Generative AI applications
Scaled beyond Italy to business units in Spain and the UK

The Highlights

Demonstrated that Generative AI delivers most value solving concrete operational problems, not replicating chat
Standardising output proved more important than enriching interaction
Modular, sub-task approach became a wider organisational best practice
Project built internal AI capability and a replicable operating model
Strong focus on wellbeing and inclusivity in day-to-day collaboration

Social Impact

Showcased how a neurodivergent auticon consultant brought a structured, modular working method that became a best practice within Veolia, while delivering tangible business value through Generative AI.