SciTransfer
Lili.AI · Project

AI-Powered Risk Detection to Prevent Costly Claims in Large-Scale Infrastructure Projects

constructionPilotedTRL 6

Imagine a digital assistant that reads every single email, meeting note, and report for a massive construction site. It looks for 'weak signals'—small warnings that something is going wrong—long before they become disasters. It's like having a super-powered alarm system that tells you a project is drifting off track before you lose millions in lawsuits.

By the numbers
100 million
Minimum project budget target (€)
54 million
Average global claim cost (€)
250 million
Target budget for breakthrough solution (€)
The business problem

What needed solving

Large-scale projects often fail to detect early warning signs in documentation, leading to aggravated issues and massive financial penalties.

The solution

What was built

A Big Data platform with NLP/ML pipelines and Microsoft 365 connectors for real-time analysis of unstructured project documents.

Audience

Who needs this

Infrastructure construction firmsLarge-scale engineering companiesIndustrial waste management operatorsProject management offices (PMO) for mega-projects
Business applications

Who can put this to work

Civil Engineering
enterprise
Target: Infrastructure developers

If you are an infrastructure developer dealing with projects over €100 million — this project developed an AI monitoring tool that detects risks in real-time from emails and reports. This prevents the aggravation of issues that lead to massive financial penalties.

Waste Management
enterprise
Target: Industrial waste plant operators

If you are a waste management operator dealing with complex engineering builds — this project developed a Big Data platform that analyzes unstructured text. It helps you identify problems early to avoid claims that average €54 million globally.

Legal Services
mid-size
Target: Construction law firms

If you are a law firm dealing with claims litigation for large projects — this project developed NLP technology that extracts actionable insights from project documentation. This allows for better-documented claims and more efficient litigation processes.

Frequently asked

Quick answers

How much does the solution cost or price?

Based on available project data, specific pricing details for the Lili.AI solution are not provided.

Can this be deployed at an industrial scale?

Yes, the project delivered a Big Data platform designed for distributed, parallel execution on large datasets using a scalable cloud-agnostic infrastructure.

What is the IP or licensing model?

Based on available project data, the specific licensing terms are not mentioned, but the technology is developed by an SME (LILI.AI).

How does it integrate with existing company tools?

The system includes developed connectors specifically for enterprise systems, with a focus on Microsoft 365 integration.

What is the timeline for deployment?

The project period runs from 2022-06-01 to 2025-05-31, with the goal of reaching TRL9.

Consortium

Who built it

The project is led by a single French SME, LILI.AI, representing a 100% industry ratio. This lean structure suggests a highly focused commercial drive, moving from TRL6 to TRL9 without the overhead of academic partners, focusing directly on industrial application and deployment.

How to reach the team

Contact LILI.AI in France

Next steps

Talk to the team behind this work.

Contact us to explore licensing opportunities for AI-driven risk management.