We’re thrilled to announce that Deix has been selected as a winning startup for the "ITALTEL DIGITAL KNOWLEDGE" challenge in Italtel’s co-innovation program!

It’s an honor to have been chosen for this opportunity, and we can’t wait to collaborate with the Italtel team. We’ll leverage our generative AI platform Jinn to enhance corporate knowledge, working side by side to co-design the solution and turn ideas into reality.

A huge thank-you to Italtel for the trust, and congratulations to the other winning startups: ML cube, B4 Group, Revolt SRL, and AstraKode.

Ready to begin this co-innovation adventure!

Proud to be among the winners of Italtel's Innovation Game

Italtel's Innovation Game

*Milan* – Artificial intelligence applied to industry met the world of academic research during the event "AI between research and business: the FAIR ecosystem," held at Politecnico di Milano. A day dedicated to strengthening the synergy between innovation and concrete application, where Deix played a leading role.

**Introducing INTEGRA Innovation for Ergonomic Analysis**

During the event, our team composed of Francesca Schweiger, Riccardo Cataldi, and Jacopo Corno presented INTEGRA, a cutting-edge project that aims to innovate the assessment of ergonomic risks in the workplace.

INTEGRA's objective is simple but ambitious: to improve workers' health and safety through artificial intelligence. Our technology analyzes videos and images to automatically evaluate operators' postures and movements, combining AI algorithms with physical models of the human body. The system can automatically calculate risk indicators based on scientifically validated scales such as REBA, RULA, and OWAS, offering an objective and powerful tool for the prevention of injuries and occupational diseases.

**Beyond Workplace Safety: A Look at the Future**

The potential of such an advanced system doesn't stop at the industrial context. The same technologies that we apply today for ergonomic analysis can be extended to other sectors, such as healthcare, for rehabilitation monitoring, and sports, for performance analysis and injury prevention for athletes.
Special thanks go to Fondazione FAIR for the opportunity and to all participants for a day full of insights and inspiration.

The AI That Puts Workplace Health at the Center

Deix at Politecnico di Milano with INTEGRA

We are thrilled to share our recent participation at WMF - We Make Future in Bologna on June 4th, an event that continues to establish itself as a reference point for technological innovation at an international level. It was a true journey into the future, exploring the latest frontiers of software and hardware that are reshaping the technological landscape.

We had the opportunity to explore stands rich with cutting-edge solutions: from the latest generation electric cars to humanoid and non-humanoid robots, including revolutionary jetpacks. Particular attention was dedicated to innovations in the world of Artificial Intelligence, a continuously evolving sector where Deix positions itself as a key player.

Our CEO, Jacopo Corno, actively contributed to this exchange of ideas by participating in a panel with Clust-ER Agrifood. During his presentation, he illustrated how the data-driven approach and mathematical modeling, pillars of our "Mathematical Intelligence," can generate concrete value and innovation in the agricultural and food sector. A clear example of how our expertise translates into practical solutions for business challenges.

Deix's presence at WMF Bologna reinforced our conviction that innovation springs from the cross-pollination of ideas and collaboration between different sectors. We are proud to be at the center of this innovative drive, ready to support companies in their digital transformation with cutting-edge solutions that are robust, explainable, and ethical, guided by our unique synergy between Artificial Intelligence and Mathematical Modeling.

Deix is here, and continues to build the future of innovation, one project at a time.

A Journey into Innovation and Mathematical Intelligence at the Service of the Future

Deix at WMF Bologna

We are proud to announce that Deix has been included in Cariplo Factory's "Reach The Goals" report. This publication, created in collaboration with important institutional partners, brings together the startups and innovative SMEs in Italy that are driving change towards the Sustainable Development Goals (SDGs) of the 2030 Agenda.

For us, this recognition confirms the value of our work: developing advanced technological solutions that not only create value for businesses, but also contribute to a more sustainable and responsible future.

**Our Concrete Contribution to Global Goals**

At Deix, we translate innovation into concrete actions that address some of the most pressing global challenges. Our inclusion in the report highlights the impact of our projects on key areas of sustainability:

- Health, Safety and Well-being at Work: Through our Varda-AI platform, we promote safer work environments. Leveraging Computer Vision, we help companies prevent accidents by proactively monitoring production areas and fostering worker well-being.
- Innovation, Industry and Resilient Infrastructure: We support companies in the manufacturing and infrastructure sectors with solutions that improve efficiency and resilience. With our DDO (Data-Driven Operations) platform, we optimize industrial processes for more conscious use of resources and more sustainable production.
- Responsible Consumption and Production: Our optimization algorithms are designed to reduce waste, from energy consumption in production cycles to logistics optimization. We help companies implement business models that are not only profitable, but also mindful of environmental impact.

**Driving Change, Together**

Being selected by Cariplo Factory motivates us to continue with even greater determination in our mission. We will continue to develop technologies that serve as an engine for sustainable economic growth and responsible innovation.
The "Reach The Goals" report is an essential resource for anyone interested in discovering the organizations that are actively building a better tomorrow.

Download the full report at this link: [https://cariplofactory.it/progetto/reach-the-goals/](https://cariplofactory.it/progetto/reach-the-goals/)

Deix Among the Companies Selected in Cariplo Factory's "Reach The Goals" Report

Innovation and Sustainability

Jacopo Corno and Mattia Satta visited the CCI France Italie - Chamber of Commerce today for the WelcomeDay of the Le Booster Startup program, alongside BioFashionTech, PARKIE and Ernesto.it – the other 3 startups selected for this edition.

This journey will accompany us until autumn and represents an important step in our internationalization strategy.

We are excited to bring our vision and solutions based on *Mathematical Intelligence* to international contexts, creating new connections and gathering valuable insights.

A special thanks to Chiara Lattuada and the entire Chamber team for their welcome and for this opportunity: we can't wait to discover what the coming months have in store for us!

Deix in the Le Booster program

C'est parti!

On April 2, during the Shareholders' Meeting, the creation of a new board was approved, composed of Marco Sciandrone, Ottavio Crivaro, and Jacopo Corno. This transition marks a new phase for our company, with the goal of strengthening the organizational structure and accelerating development in the coming years.


Leading Deix as the new CEO will be **Jacopo Corno** ([https://www.linkedin.com/in/jacopo-corno/](https://www.linkedin.com/in/jacopo-corno/)), PhD in Computational Engineering, with 11 years of experience in mathematical modeling, numerical methods, and optimization, the first employee of the company and now a central figure in building our business solutions. Jacopo takes on this new role alongside the experience and vision of **Marco Sciandrone** ([https://www.linkedin.com/in/marco-sciandrone-1777a4234/](https://www.linkedin.com/in/marco-sciandrone-1777a4234/)), Professor of Operations Research at Sapienza University of Rome, founder of Deix and now Chairman of the board, and **Ottavio Crivaro** ([https://www.linkedin.com/in/ottaviocrivaro/](https://www.linkedin.com/in/ottaviocrivaro/)), entrepreneur and advisor with over twenty years of experience in innovation and technology transfer, representing Ottozerouno srl, an innovative company founded in 2022 that recently entered Deix's cap table.


*"At Deix, we have always believed in the value of concrete innovation. I thank the shareholders for their trust in me. Taking on this role is a great responsibility, but also an opportunity to bring even more energy, vision, and structure to a company that has everything it needs to grow."* - Jacopo Corno


In the new structure, Jacopo will work closely with the team and partners, supported by **Luca Pasquale** as Chief Technology Officer and **Mattia Satta** as Chief Operating Officer.

*"Deix was created to put mathematics and artificial intelligence at the service of businesses. This new structure is the natural step to continue growing, while maintaining our values and the quality of our work."* - Marco Sciandrone


*"I have seen many innovative companies, but few with the potential and expertise of Deix. I am happy to contribute to the growth of a company that combines research, talent, and vision."* - Ottavio Crivaro


With this reorganization, we want to give even more visibility to the technical and human value of our team, continuing to work alongside companies with Mathematical Intelligence solutions, which combine mathematical modeling, advanced statistics, algorithmic mathematics, data science, and artificial intelligence in a single integrated approach.


Special thanks go to **Fabio Fregonese**, who in recent years has led Deix as sole administrator with professionalism, passion, and dedication, accompanying the company through a phase of continuous growth. Fabio will continue to be part of our team, contributing with his experience to activities related to administrative and financial management.


The future is yet to be written, and we are ready to experience it with even more energy.


*About Deix srl* - [www.deix.ai](https://www.deix.ai)

Deix is a startup from Sapienza University of Rome, founded in 2020 with the aim of revolutionizing the way companies approach digital transformation, integrating advanced skills in applied mathematics, optimization, and numerical simulation with the most modern artificial intelligence and machine learning techniques. This synergy, "Mathematical Intelligence," not only improves the comprehensibility and ethics of AI models but also significantly increases their reliability and precision. In addition to working on customized digital innovation projects for partners and clients, Deix has developed the JINN platform that allows creating and managing AI Agents quickly and reliably.


*About Ottozerouno srl* - [www.ottozerouno.com](https://www.ottozerouno.com)

Ottozerouno is a company specialized in technology transfer and business development, created to bridge the gap between cutting-edge research and the market. The main objective is to transform ideas into concrete solutions: selecting and enhancing the most promising innovations, supporting startups in their growth path, and offering consulting services to companies that wish to remain competitive in a rapidly evolving industrial landscape.

New board is born and Jacopo Corno is the new CEO

Deix renews itself

Three intense days, a vibrant capital, and an international ecosystem that lives and breathes innovation: our participation in **SMAU | Italy RestartsUp** in London was a true concentration of stimuli, connections, and visions about the future. Deix was selected among Italian startups invited to represent "made in Italy" innovation in the United Kingdom, thanks to **SMAU**'s organization and the support of **ITA – Italian Trade Agency**.

Representing us were **Jacopo Corno** (Head of Business Solutions, CEO Delegate) and **Beatrice Bianchi** (Data Scientist), who experienced the entire event, from networking at the Italian Embassy to pitches and panels within the suggestive space of **Protein Studios**. But perhaps the most stimulating moment was the third day: a true tour of London's innovation scene, among hubs, incubators, and visionary organizations. In particular, we were impressed by the visit to **Earls Court**, where an urban project is taking shape that combines sustainability, cutting-edge architecture, and new models of collaboration between public, private, and community stakeholders.

London confirmed itself as a fertile and dynamic environment, where innovation is experienced as something everyday, rooted in a culture of action. For an organization like Deix, it was valuable to engage with different approaches, gather ideas, and create new connections with potential international partners and stakeholders.

We return home with many concrete ideas and contacts, but above all with the confirmation that our **mix of mathematical intelligence, creativity, and technology** can also speak to a global audience. SMAU London is a bridge between worlds, and we are proud to be part of it and to be called upon to make our contribution.

What we bring back from SMAU London 2025

From Milan to London

**Interested in This Technology?**

If you want to learn more or collaborate with us on this project, contact us at info@deix.ai.

Imagine having to solve a complex problem, such as organizing the optimal employee shift schedule in a company while minimizing costs and complying with all legal and productivity constraints. For an operations research expert, this means transforming the request into a mathematical model, with precise equations and constraints, and then delegating the solution to specialized software.

But what if artificial intelligence could perform this translation automatically?

This is where **LLM4OR** comes into play—a Deix research project exploring the use of **Large Language Models (LLMs)** to interpret problems described in natural language and convert them into **ready-to-use mathematical models**.


*The idea is as simple as it is ambitious: Can we teach AI to perform our analysis and formalization work?*

Not to replace human intelligence, but to make it more efficient and faster.

### The Core of the Project: Language Models and Optimization

**How Does an LLM Work?**

A **Large Language Model (LLM)** like ChatGPT does not "think" or "understand" in the human sense of the terms. It **does not reason like an optimization expert** who analyzes a problem, reflects on its implications, and consciously formulates a mathematical model.

Instead, an LLM functions as a highly advanced sentence completer. It works by associating word sequences with other statistically probable sequences based on all the training data it has seen.

*A useful analogy?*

*Imagine a tourist in a foreign country who doesn’t speak the local language. They have a phrasebook with pre-translated sentences: they don’t truly understand the meanings but know that to ask for the check at a restaurant, they must say, "The check, please." If the situation changes slightly (e.g., a waiter asks if they want to pay by card or cash), they might be confused.*

An LLM works in a similar way: it doesn’t truly "understand" the problem, but it knows which type of response is most probable based on its training data.

**LLMs for Operations Research**

Despite this statistical approach, LLMs can be surprisingly effective. To test whether an LLM can simulate the ability to translate an optimization problem into a mathematical model, we:

- **selected an open-source model** (Llama3-8B-Instruct) to evaluate its effectiveness compared to proprietary models like ChatGPT,
- **used a public dataset** containing optimization problems already translated into mathematical models, providing the model with clear examples,
- **created a custom dataset** with more realistic and complex problems to further improve the model's capabilities,
- **fine-tuned the model**, allowing it to "study" the new data to enhance its translation accuracy.

It's important to clarify: we did not "teach" the model to think like an expert but trained it to recognize and replicate effective translation patterns.

A system capable of converting problems described in natural language into mathematical models.

### The Results: AI vs. Human Experts?

We compared our model with ChatGPT-3.5 and ChatGPT-4o on a set of problems, evaluating:
- correct identification of variables and the objective function
- precise translation of mathematical constraints
- ability to generate executable code for solving the problem.

Our model outperformed ChatGPT-3.5 and, thanks to fine-tuning on custom data, even **surpassed ChatGPT-4o's capabilities**.


*But what does this mean in practice?*

*It means that a user could describe a problem in plain language and automatically receive a model ready to be solved by optimization software.*


### Applications: Where Can This Technology Be Used?

Today, the project is still in an experimental phase, but its applications are vast:
- **Supporting our experts**: At Deix, this technology could **accelerate our work **by reducing the time required for the initial modeling phase.
- **Integration into [JINN](https://deix.ai/solutions/products/jinn)**: Deix's AI platform for creating multi-purpose AI agents now includes features for training and fine-tuning a dedicated model based on an open-source one, not just for optimization problems.


### A First Step Toward Optimization Automation

The LLM4OR experiment has demonstrated that LLMs can support optimization by translating problems into mathematical models with increasing accuracy.


🚀 This isn’t about replacing human intelligence but enhancing it, providing a tool that speeds up and simplifies the work of experts.

💡 For Deix, this reaffirms our mission: exploring AI's potential to create innovative and practical solutions.



Articles and news