Webinar Modern AI Models: Large Language Models (LLMs)

On 1 July 2026, the MCE Community hosted the webinar about Modern AI Models: Large Language Models (LLMs).

Agenda

• Introduction – Giorgio Prister, President of the MCE Community
• Presentation – Mauro Lavezzari, AI Solutions Architect Consultant
• Moderator – Alessandra de Seneen, Member of the MCE Community Executive Committee
• Closing remarks and next steps – Giorgio Prister

The webinar aimed to demystify AI models, helping participants gain a clear understanding of both the opportunities and limitations of Large Language Models (LLMs) in real-world applications.

Key topics covered:

• An overview of the evolution of AI models, from early neural networks to transformer architectures
• The fundamental principles behind how Large Language Models work
• How LLMs are trained, fine-tuned and adapted to specific use cases
• Contextualisation techniques, including Retrieval-Augmented Generation (RAG)
• Best practices for interacting effectively with LLMs through prompting and inference
• Resource considerations, including token usage and computational requirements
• Monitoring and controlling model outputs, with a focus on risk management
• The LLM lifecycle, from development through to deployment
• Practical examples and real-world use cases

Resources

• Presentation slides
• Session recording

Further information about the MCE Community is available at www.mcecommunity.eu, including details on how to become a member: www.mcecommunity.eu/become-a-member/.

For enquiries, please contact info@majorcities.eu.