{"id":5292,"date":"2025-04-09T10:32:19","date_gmt":"2025-04-09T08:32:19","guid":{"rendered":"https:\/\/aiheroes.it\/2025\/?page_id=5292"},"modified":"2025-05-26T10:35:30","modified_gmt":"2025-05-26T08:35:30","slug":"speakers","status":"publish","type":"page","link":"https:\/\/aiheroes.it\/2025\/speakers\/","title":{"rendered":"Speakers"},"content":{"rendered":"<h1>AI Heroes 2025 Speakers<\/h1>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_friese.png\" alt=\"\"><\/p>\n<h3>Peter Friese<\/h3>\n<p>Staff Developer Relations Engineer, Google<\/p>\n<div>\n<p>Peter is a Staff Developer Advocate on the Firebase at Google, helping developers build amazing experiences and high quality apps using Firebase and AI. With a passion for empowering developers and fostering innovation, Peter works tirelessly with the Firebase team to make his vision of \u201ccutting short the time to magic\u201d a reality. He has written code in BASIC, C, ObjectPascal, Java, Kotlin, Xtext, JavaScript, TypeScript, Objective-C, and a number of home-grown DSLs &#8211; but his all-time favourite is Swift.<\/p>\n<p><a href=\"https:\/\/x.com\/peterfriese\" class=\"button-link\" target=\"blank\">X<\/a> | <a href=\"https:\/\/www.linkedin.com\/in\/peterfriese\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> | <a href=\"https:\/\/github.com\/peterfriesee\" class=\"button-link\" target=\"blank\">Github<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>Beyond Prompts: Building Intelligent Applications with Genkit and the Model Context Protocol<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example14\">Abstract<\/button><\/p>\n<div id=\"modal-example14\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Beyond Prompts: Building Intelligent Applications with Genkit and the Model Context Protocol<\/h4>\n<p>LLMs have democratized AI, making it more accessible for everyone. But today\u2019s chat bots still feel very disconnected. Wouldn\u2019t it be great if you could use AI to tap into your personal knowledge and data, and use it to drive the tools you already know and love? Imagine using a chat bot to create your next pitch deck, or generating bespoke 3D scenes for your next home decoration project using inexpensive tools like Blender. In this talk, I&#8217;ll show you how this is possible with tools like Genkit and MPC, the Model Context Protocol.<\/p>\n<p>You will learn:<\/p>\n<ul>\n<li>What Genkit is and how its key abstractions make building AI apps easier and faster<\/li>\n<li>How you can leverage MCP to allow LLMs to interact with existing apps and systems<\/li>\n<li>How to architect intelligent applications that orchestrate complex tasks by connecting to and reusing your existing APIs, data sources, and specialised tools.<\/li>\n<\/ul>\n<p>I will even demo an agentic app built using Genkit, MCP, Swift, and Keynote that you can use to craft presentation decks using just natural language &#8211; including doing the research!<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_lerro-1.png\" alt=\"\"><\/p>\n<h3>Francesco Lerro<\/h3>\n<p>Software Architect, TheFork &#8211; TripAdvisor Group<\/p>\n<div>\n<p>A software architect who&#8217;s been around so long he&#8217;s witnessed more programming languages come and go than he can remember (20+ years, if we must count). He&#8217;s built things that millions of people use daily, probably even while you&#8217;re reading this. Leader of the local AWS User Group, where he tries to convince other nerds that the cloud isn&#8217;t just &#8220;someone else&#8217;s computer.&#8221; When he&#8217;s not sketching architectures on bar napkins or explaining to his grandmother what a microservice is, you&#8217;ll find him speaking at tech conferences, desperately trying to make the audience laugh with database jokes. His mission? Using technology to solve real-world problems, or at least that&#8217;s what he tells his family to justify all the time spent in front of screens.<\/p>\n<p> <a href=\"https:\/\/www.linkedin.com\/in\/lerro\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> | <a href=\"https:\/\/github.com\/flerro\" class=\"button-link\" target=\"blank\">Github<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>How TheFork is Revolutionizing Dining Experiences with Generative AI<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example12\">Abstract<\/button><\/p>\n<div id=\"modal-example12\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">How TheFork is Revolutionizing Dining Experiences with Generative AI<\/h4>\n<p>What happens when Generative AI meets the world of dining? At TheFork, we\u2019ve transformed restaurant discovery into a personalized experience for every user. This talk will take you through our exciting journey of adopting GenAI\u2014balancing innovation with privacy, legal compliance, and the creation of a solid AI blueprint to support multiple internal initiatives. We\u2019ll share how we\u2019ve leveraged diner reviews to enhance the user experience, from generating smarter recommendations to crafting personalized restaurant descriptions. Join us as we explore the challenges, lessons learned, and the strategies that are shaping TheFork into an intelligent, user-centric dining advisor. Join us as we explore the challenges, lessons learned, and the strategies that are shaping TheFork into an intelligent, user-centric dining advisor. <\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_denobili.png\" alt=\"\"><\/p>\n<h3>Cristiano De Nobili<\/h3>\n<p>Freelance Lead Scientist &#038; Scientific Advisor<\/p>\n<div>\n<p>Cristiano is a Theoretical Physicist with a PhD in Quantum Information Theory from SISSA in Trieste, Italy. With over 9 years of experience in Deep Learning, he is currently the Lead AI Scientist at Pi School, working mainly on AI applied to language, space and climate challenges. He is a lecturer in Deep Learning at the Master in High-performance Computing (ICTP\/SISSA, Trieste) and in Quantum Machine Learning at Ca\u2019 Foscari College School. He is the Scientific Advisor for Scientifica VC, an Italian fund investing in deep-tech startups His focus has always been on emerging technologies, AI and Quantum tech, with collaborations ranging from European Space Agency to the SIOS Remote Sensing Centre in the Svalbard Islands. In spare time he is a pilot of airplanes and gliders. He runs a newsletter on LinkedIn: Beyond Entropy.<\/p>\n<p> <a href=\"https:\/\/www.linkedin.com\/in\/cristiano-de-nobili\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> | <a href=\"https:\/\/x.com\/denocris\" class=\"button-link\" target=\"blank\">X<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>Physics and Quantum Inspired AI<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example20\">Abstract<\/button><\/p>\n<div id=\"modal-example20\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Physics and Quantum Inspired AI<\/h4>\n<p>This 30-minute talk will motivate and introduce Physics and Quantum methods that will improve current machine learning algorithms and perhaps help solve the growing energy demands of LLMs. Starting from Landauer&#8217;s principle, we will discuss the limitations of current semiconductor technologies and how emerging computing paradigms could power future training and inference. <\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_gilli.png\" alt=\"\"><\/p>\n<h3>Luca Gilli<\/h3>\n<p>CTO, Clearbox AI<\/p>\n<div>\n<p>I am the co-founder of Clearbox AI, a company specializing in synthetic data generation solutions to drive innovation and enhance data privacy. I&#8217;ve lived for more than 10 years in the Netherlands where I got my PhD in applied sciences and worked as a scientific software developer. <\/p>\n<p>Outside of work, I enjoy hiking in the beautiful Piedmontese mountains. I&#8217;m also passionate about farming, with a special interest in experimenting with hydroponic techniques.<\/p>\n<p> <a href=\"https:\/\/x.com\/virgillus\" class=\"button-link\" target=\"blank\">X<\/a> | <a href=\"https:\/\/www.linkedin.com\/in\/luca-gilli\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> | <a href=\"https:\/\/github.com\/gillus\" class=\"button-link\" target=\"blank\">X<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>Replica Italia: how to build a digital twin of the Italian population<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example23\">Abstract<\/button><\/p>\n<div id=\"modal-example23\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Replica Italia: how to build a digital twin of the Italian population<\/h4>\n<p>Replica Italia is a synthetic, privacy-safe digital twin of the Italian population. This presentation explores the technical challenges and data sources involved in its development.\u200b<br \/>\nCreating a digital twin required integrating diverse datasets: we utilised open data, statistical modelling, and simulations to represent demographic, behavioural, and geolocation attributes. Key data sources included public demographic statistics, consumer behaviour studies, and geospatial information.\u200b The resulting platform provides instant access to AI-generated panels of over 60 million synthetic Italian users, facilitating concept testing, surveys, and consumer response simulations. It also enables the enrichment of customer profiles and the creation of high-quality synthetic audiences for targeted advertising, all without accessing personal data.<br \/>\nThis talk provides an in-depth exploration of the methodologies employed to integrate diverse data sources in creating a national-scale digital twin.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_dotti.png\" alt=\"\"><\/p>\n<h3>Piero Dotti<\/h3>\n<p>CTO, Monade srl<\/p>\n<div>\n<p>I&#8217;m a Software Engineer specialized in AI and Computer Vision, with a strong background in web and AI technologies. Over the past two years, I&#8217;ve focused on building GenAI applications\u2014working with LLMs, RAG, and AI agents.<\/p>\n<p>I&#8217;m the co-founder and CTO of three companies:<\/p>\n<ul>\n<li><strong>M\u00f2nade<\/strong>, a 30-person consultancy delivering custom software and AI Agents<\/li>\n<li><strong>Elf Games<\/strong>, a game studio with two internationally recognized titles<\/li>\n<li><strong>Elysia<\/strong>, a SaaS platform that helps companies unlock internal knowledge using Generative AI<\/li>\n<\/ul>\n<p><a href=\"https:\/\/x.com\/ProGiEmmeh\" target=\"blank\">X<\/a> | <a href=\"https:\/\/www.linkedin.com\/in\/piero-dotti\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> | <a href=\"https:\/\/github.com\/ProGM\" class=\"button-link\" target=\"blank\">X<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>Scaling Vector Search with PostgreSQL: A Deep Dive into pgvector Optimization<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example24\">Abstract<\/button><\/p>\n<div id=\"modal-example24\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Scaling Vector Search with PostgreSQL: A Deep Dive into pgvector Optimization<\/h4>\n<p><strong>Are you building AI applications that need a reliable, scalable vector store? This talk provides a comprehensive guide to configuring PostgreSQL as an optimal vector store for AI applications<\/strong><span>\u00a0<\/span>using the pgvector extension.<\/p>\n<p>We&#8217;ll begin with a brief introduction to vector stores and PostgreSQL fundamentals before diving into the pgvector extension and its capabilities. The presentation will explore essential vector operations and compare indexing approaches (<strong>HNSW vs. IVFFlat<\/strong>), offering practical guidance on hyperparameter tuning for your specific use cases.<\/p>\n<p>We&#8217;ll also cover advanced optimization techniques including:<\/p>\n<ul>\n<li>Reduced precision<\/li>\n<li>Quantization methods<\/li>\n<li>Various scaling strategies such as partitioning, sharding, and replication to handle growing data volumes<\/li>\n<\/ul>\n<p>We&#8217;ll also see a real-world example of a semantic search application using pgvector, demonstrating how to implement and optimize it for production.<\/p>\n<p><strong>Whether you&#8217;re implementing semantic search, recommendation systems, or other vector-based AI applications, you&#8217;ll leave with actionable knowledge to configure PostgreSQL as a high-performance, production-ready vector database.<\/strong><\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_caglio-pozzoli.png\" alt=\"\"><\/p>\n<div>\n<p><h12 style=\"font-size: 50px; color: #ff0a6a; font-family: Manrope; font-weight: bold;\">Andrea Caglio<\/h12><\/p>\n<h4>AI &#038; Software Engineer, Intr\u00e9 srl | Memoria <\/h4>\n<p>I am a software &#038; AI engineer with a strong passion for Artificial Intelligence and Machine Learning. At Intr\u00e9, I played a key role in the creation of Memoria, the business unit dedicated to developing tailored AI solutions. Here, I focus on building innovative AI applications that address real-world challenges.<\/p>\n<p>Beyond development, I believe in knowledge sharing: I enjoy showcasing what AI can achieve today, which is why I frequently speak at conferences, sharing practical experiences and use cases.<\/p>\n<p> <a href=\"https:\/\/www.linkedin.com\/in\/andrea-caglio\/\" class=\"button-link\" target=\"blank\" >LinkedIn<\/a> <\/p>\n<hr \/>\n<p><h12 style=\"font-size: 50px; color: #ff0a6a; font-family: Manrope; font-weight: bold;\">Luca Pozzoli<\/h12><\/p>\n<h4>Software &#038; AI Engineer, Intr\u00e9 srl | Memoria <\/h4>\n<p>My academic path allowed me to obtain a master&#8217;s degree in mathematics, while my working career led me to coding.<br \/>\nCurrently working as an AI &#038; software engineer, I focus on building AI solutions: starting from the prototype, features are added incrementally to build the final product. I like comparing this to the work of a craftsman, who keeps on refining and improving its own work.<br \/>\nWhat else? In my spare time I like watching movies, listening to music and playing boardgames.<\/p>\n<\/p>\n<hr \/>\n<h3>Back to the Prompt: Rewriting the Future of AI with Real-Time Knowledge<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example25\">Abstract<\/button><\/p>\n<div id=\"modal-example25\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Back to the Prompt: Rewriting the Future of AI with Real-Time Knowledge<\/h4>\n<p>What if your AI assistant could travel through time, rewriting the rules of documentation as it goes?<br \/>\nIn this talk, we\u2019ll take you on a journey to the future of knowledge management, where your assistant doesn&#8217;t rely on outdated documents. Instead, it can ingest real-time information via chat, making sure that this new data takes priority over the old. Powered by cutting-edge Generative AI, LLMs, Bots, and a Retrieval-Augmented Generation (RAG) architecture, our system is capable of time-traveling knowledge, collecting, structuring, and storing it as the ultimate source of truth.<\/p>\n<p>We\u2019ll dive into the research and technical architecture that made it possible, exploring how we integrate dynamic knowledge injection, prioritize real-time inputs, and maintain consistency across the system. You\u2019ll learn how we built an AI assistant that adapts to evolving needs without compromising on reliability or user experience.<\/p>\n<p>So, buckle up! We\u2019re about to take your AI into the present. No flux capacitor required!<\/p>\n<p>Target audience: developers, ML engineers, product managers.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_caranzano.png\" alt=\"\"><\/p>\n<h3>Massimiliano Caranzano<\/h3>\n<p>Artificial Intelligence Account Executive EMEA South, Cisco Systems<\/p>\n<div>\n<p>I&#8217;m an electronic engineer who has been working in IT Innovation since the last 30 years at international level.<br \/>\nI had the luxury to ride the internet, mobility and digital revolutions. Since 5 years I look after AI in Customer Experience and recently took the responsibility of being an AI Sales for the south EMEA countries at Cisco Systems.<\/p>\n<p> <a href=\"https:\/\/www.linkedin.com\/in\/massimilianocaranzano\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> <\/p>\n<\/p>\n<hr \/>\n<h3>Internet of Agents: the role of the network in the AI revolution<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example21\">Abstract<\/button><\/p>\n<div id=\"modal-example21\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Internet of Agents: the role of the network in the AI revolution<\/h4>\n<p>We are in the AI Agentic phase, where AI entities are able to autonomously reason and act (ReAct) and this will literally change the way we Live, Play and Work.  A new army of Autonomous Digital Workes will join the humans at work as well as in private life changing the entire IT industry: software, hardware, infrastructure and services. This moltitude of digital resources will require a new &#8220;internet&#8221; working differently, al layer 7, able to Connect, Secure, Observe and foster Collaboration exactly as it was in the beginning of the internet revolution. We are at the dawn of the IOA, Internet of Agents.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_dispenza.png\" alt=\"\"><\/p>\n<h3>Davide Dispenza<\/h3>\n<p>CTO, Volcanic Minds<\/p>\n<div>\n<p>Davide is a seasoned software engineer and co-founder of Volcanic Minds, a digital experience company based in Turin. With 15+ years of experience, he has led the development of complex web and mobile applications using mainly JavaScript and Node.js. Previously CTO at epiCura, he helped scale the healthtech platform from startup to national growth. He brings deep expertise in frontend engineering, architecture, and team leadership. Passionate about building tech that solves real problems, Davide now focuses on high-impact digital products for startups and brands. He\u2019s also a keen photographer and metal guitarist. At this event, he\u2019ll share lessons from his journey bridging product vision and engineering execution.<\/p>\n<p><a href=\"https:\/\/x.com\/DDVolcanicMinds\" class=\"button-link\" target=\"blank\">X<\/a> | <a href=\"https:\/\/www.linkedin.com\/in\/davidedispenza\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>Agent Collaboration Across Frameworks: Interoperability with CrewAI, LangGraph, and Google A2A<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example26\">Abstract<\/button><\/p>\n<div id=\"modal-example26\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Agent Collaboration Across Frameworks: Interoperability with CrewAI, LangGraph, and Google A2A<\/h4>\n<p>Modern AI development is rapidly shifting from isolated LLM prompts to orchestrated systems of collaborative agents. But with so many tools and frameworks emerging, interoperability remains a key challenge. In this talk, we introduce three powerful and complementary technologies: CrewAI, a lightweight framework for autonomous multi-agent collaboration; LangGraph, a graph-based orchestration engine for LLM workflows; and Google\u2019s Agent-to-Agent (A2A) protocol, a new open standard enabling agents to discover and communicate across frameworks and infrastructures.<\/p>\n<p>You\u2019ll learn how each technology works, what problems they solve, and how they differ in design and application. The final part of the talk is a live demo: an AI agent that receives a user request and coordinates with two separate agent stacks\u2014one built with CrewAI and another with LangGraph\u2014via the Google A2A protocol, showcasing seamless cross-framework problem-solving in action.<\/p>\n<p>Audience: AI developers, architects, and technical leads building agent-based systems or evaluating agent frameworks. Length: 40 minutes. Innovation: This is a brand-new talk featuring a live demo of multi-framework agent interoperability using Google A2A. Takeaways: Attendees will leave with a clear understanding of CrewAI, LangGraph, and A2A; practical insights on when and how to use each; and a blueprint for building scalable, interoperable, multi-agent systems.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_antonini.png\" alt=\"\"><\/p>\n<h3>Daniele Antonini<\/h3>\n<p>Head of Engineering,  Translated<\/p>\n<div>\n<p>Hi, I\u2019m Daniele &#8211; I\u2019m a Head of Engineering with 15+ years of experience in backend development and DevOps \u2014 mostly in Java, but I\u2019ve been having a lot of fun with Node.js over the past couple of years. I\u2019ve led teams through complex challenges, building scalable systems and navigating fast-changing environments. Over the years, I\u2019ve seen it all: unexpected pivots, hard-won victories, and plenty of tricky problems. My approach is simple \u2014 identify areas for growth, anticipate change before it hits, and solve problems at the root so they stay solved. I\u2019m passionate about team culture. I thrive in collaborative environments where people feel empowered to do their best work. I bring strong analytical skills to the table \u2014 but I\u2019m also very aware I don\u2019t know everything (and that\u2019s half the fun). I believe the journey matters just as much as the outcome. I\u2019m endlessly curious and love working with people from different backgrounds. I see diversity as a source of creativity \u2014 and I\u2019m always up for exploring new ideas, especially when they challenge how we build software.<\/p>\n<p><a href=\"https:\/\/x.com\/daniele_ntn\" class=\"button-link\" target=\"blank\">X<\/a> | <a href=\"https:\/\/www.linkedin.com\/in\/danieleantonini\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> | <a href=\"https:\/\/github.com\/dantonini\/user-story-matrix\/\" class=\"button-link\" target=\"blank\">Github<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>Coding with AI: How to Get Predictable Results <\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example28\">Abstract<\/button><\/p>\n<div id=\"modal-example28\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Coding with AI: How to Get Predictable Results<\/h4>\n<p>AI coding assistants like Copilot, ChatGPT, and Cursor have transformed how we write software \u2014 but often in unpredictable ways. Vague prompts, inconsistent results, and scattered workflows are now part of our daily reality. The promise of AI-powered development is huge, but without structure, it&#8217;s easy to fall into chaos.<\/p>\n<p>In this talk, I\u2019ll introduce User Story Matrix (USM) \u2014 an open-source CLI tool that helps developers orchestrate AI-assisted development with clarity and control. USM lets you define structured user stories, generate implementation blueprints, and guide AI tools through testable, repeatable steps.<br \/>\nWhether you&#8217;re working solo or in a team, USM gives you a lightweight, developer-first workflow to make AI coding deliberate and scalable \u2014 not just experimental.<br \/>\nThis talk is aimed at developers, tech leads, and AI tool builders looking to reduce noise and get real results from AI coding. You\u2019ll walk away with a fresh mindset, a practical CLI demo, and a repeatable process to bring predictability back to your AI-assisted workflow.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_cugliari.png\" alt=\"\"><\/p>\n<h3>Giovanni Cugliari<\/h3>\n<p>CPTO, Vedrai<\/p>\n<div>\n<p>Chief Product &#038; Technology Officer, driving innovation through strategic product vision and cutting-edge AI solutions.<br \/>\nStartup Co-founder and Strategic Advisor, with 20+ years of experience in creating impactful, data-driven technologies.<br \/>\nPhD in AI, Professor, Editorial Board Member and Author of 100+ scientific publications and 3 books.<br \/>\nPassionate about using technology to solve complex challenges and shape a smarter, more connected future.<\/p>\n<p> <a href=\"https:\/\/www.linkedin.com\/in\/giovanni-cugliari-333b6664\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> <\/p>\n<hr \/>\n<h3>The composite AI-product stack: Building intelligent systems with agents and generative AI<br \/>\n<\/h3>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example18\">Abstract<\/button><\/p>\n<div id=\"modal-example18\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">The composite AI-product stack: Building intelligent systems with agents and generative AI<br \/>\n<\/h4>\n<p>As individuals and organizations strive to make smarter, faster decisions, AI is evolving beyond prediction into a new era of causal, intelligent, and collaborative decision-making. This session explores how developers can build cutting-edge Decision Intelligence Platforms by combining three key technologies. First, we&#8217;ll look at how graph analytics uncover causal relationships in data, revealing patterns and dependencies that power smarter insights. Next, we&#8217;ll dive into a simulation engine that enables scalable scenario planning, helping teams test \u201cwhat-if\u201d situations before acting. Finally, we\u2019ll explore generative data storytelling and an alerting and recommendation system that transforms raw data into meaningful, real-time narratives and guidance. Together, these elements create a platform that doesn\u2019t just react to data\u2014but understands it, plans around it, and collaborates with users to make proactive decisions.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_manasseri.png\" alt=\"\"><\/p>\n<h3>Benedetto Manasseri<\/h3>\n<p>AI Engineer, Datapizza<\/p>\n<div>\n<p>Benedetto is a Computer Engineer with a strong background in software development and a deep focus on Artificial Intelligence. He holds a Master\u2019s degree in Computer Engineering with a specialization in Data Science &amp; AI from Politecnico di Torino, where he developed a solid foundation in machine learning, data processing, and intelligent systems. He currently works as an AI Engineer at Datapizza, where he helps companies unlock the value of Generative AI by designing and building production-ready solutions, collaborating with an exceptional team of talented engineers and AI experts to bring ideas from prototype to production. Over the past year, he has led the development of multi-agent chatbots in enterprise environments, combining LLMs, advanced RAG strategies and powerful evaluation pipelines to deliver real-world impact.<\/p>\n<p><a href=\"https:\/\/x.com\/benemana?s=21&amp;t=l_pFIGFkUOFd1JTtZz_bvA\" class=\"button-link\" target=\"blank\">X<\/a> | <a href=\"https:\/\/www.linkedin.com\/in\/bdtmns\" class=\"button-link\" target=\"blank\">LinkedIn<\/a><\/p>\n<hr \/>\n<h3>How to (not) fail a GenAI project: practical lessons and technical insights from building and evolving Multi-Agent Chatbots in production<\/h3>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example19\">Abstract<\/button><\/p>\n<div id=\"modal-example19\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">How to (not) fail a GenAI project: practical lessons and technical insights from building and evolving Multi-Agent Chatbots in production<\/h4>\n<p>Why do even successful GenAI projects often plateau after reaching production? Moving from PoC to a live system is only the beginning \u2014 the real challenge lies in scaling it, making it <strong>trustworthy<\/strong>, and\u00a0 <strong>continuously improving<\/strong> its impact. Whether you\u2019re navigating your first demo or already running a GenAI solution in production, this talk is for you. Here I\u2019ll share hard-earned lessons from building production-grade <strong>multi-agent chatbots <\/strong>(e.g. \u201ctalk-with-your-documents\u201d) in a corporate environment \u2014 lessons grounded in hands-on experience, packed with <strong>practical tips <\/strong>and references to GenAI <strong>tools and frameworks <\/strong>that actually work. We\u2019ll cover:<\/p>\n<ul>\n<li>why involving business stakeholders <strong>early and often <\/strong>is not just a nice-to-have, but a critical success factor \u2014 and <em>how to do it<\/em>.<\/li>\n<li>How to build robust <strong>evaluation pipelines <\/strong>using real user data and expert input to assess relevance, accuracy, and overall system performance <em>over time<\/em>.<\/li>\n<li>How to strike the <em>right balance<\/em> between elegant simplicity and complex <strong>agents architectures<\/strong>, with a focus on composable <strong>patterns <\/strong>\u00a0and <strong>advanced strategies for RAG <\/strong>(chunking, pre-retrieval, post-retrieval, and more).<\/li>\n<li>The main challenges of\u00a0 <em>unstructured data<\/em> \u2014 and how\u00a0<strong>smart preprocessing <\/strong>can be helpful in compensating for poor document quality.<\/li>\n<li><strong>Post-deployment <\/strong>strategies: onboarding users, increasing trust through <strong>transparency <\/strong>(think interactive source tracing and agent flow visualization), and iterating based on <strong>real-world queries and feedback.<\/strong>\u00a0<\/li>\n<\/ul>\n<p>This is a new, original talk for AI Heroes, aimed at developers, AI engineers, and product teams building GenAI solutions. Get ready for a session filled with hands-on advice and real-world lessons learned from taking GenAI projects to production across a variety of contexts and scenarios.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_fabbiani.png\" alt=\"\"><\/p>\n<h3>Emanuele Fabbiani<\/h3>\n<p>Head of AI, xtream<\/p>\n<div>\n<p>Emanuele is an engineer, researcher, and entrepreneur with a passion for artificial intelligence. He earned his PhD by exploring time series forecasting in the energy sector and spent time as a guest researcher at EPFL in Lausanne. Today, he is co-founder and Head of AI at xtream, a boutique company that applies cutting-edge technology to solve complex business challenges. Emanuele is also a contract professor in AI at the Catholic University of Milan. He has published eight papers in international journals and contributed to over 30 international conferences worldwide. His engagements include AMLD Lausanne, ODSC London, WeAreDevelopers Berlin, PyData Berlin, PyData Paris, PyCon Florence, the Swiss Python Summit in Zurich, and Codemotion Milan. Emanuele has been a guest lecturer at Italian, Swiss, and Polish universities.<\/p>\n<p><a href=\"https:\/\/x.com\/donlelef\" class=\"button-link\" target=\"blank\">X<\/a> | <a href=\"https:\/\/www.linkedin.com\/in\/emanuelefabbiani\/\" class=\"button-link\" target=\"blank\" >LinkedIn<\/a> | <a href=\"https:\/\/github.com\/donlelef\" class=\"button-link\" target=\"blank\" >Github<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>Beyond Basic RAG: HyDE, Visual Embeddings, and Other Tricks<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example17\">Abstract<\/button><\/p>\n<div id=\"modal-example17\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Beyond Basic RAG: HyDE, Visual Embeddings, and Other Tricks<\/h4>\n<p>The foundational<span>\u00a0<\/span><strong>RAG architecture<\/strong><span>\u00a0<\/span>we all know &#8211; built on embeddings, vector databases, retrieval algorithms, and generative models &#8211; served us well in 2023. Now it&#8217;s time to explore the powerful enhancements that have emerged to take RAG to the next level.<\/p>\n<p>We&#8217;ll explore<span>\u00a0<\/span><strong>HyDE<\/strong>, an approach that leverages an LLM to generate hypothetical documents, creating a stronger bridge between user queries and relevant content. The result is a marked improvement in retrieval accuracy without requiring additional models.<\/p>\n<p><strong>Visual content handling<\/strong><span>\u00a0<\/span>gets a major upgrade through advanced embedding techniques, particularly with the introduction of<span>\u00a0<\/span><strong>ColPali<\/strong>. This retrieval model works directly with document images, using vision-language models to create rich, contextual embeddings from document pages. It&#8217;s particularly powerful when dealing with PDFs, scanned documents, and other visually structured content that traditional RAG systems struggle with.<\/p>\n<p>For those focused on efficiency, we&#8217;ll examine<span>\u00a0<\/span><strong>SPLADE<\/strong>, a neural retrieval model that creates sparse representations of both documents and queries. By combining the speed advantages of traditional inverted indexes with the accuracy of modern neural approaches, SPLADE offers a compelling solution for production environments.<\/p>\n<p>The discussion isn&#8217;t just theoretical &#8211; we&#8217;ll ground everything in practical implementation. Through<span>\u00a0<\/span><strong>code snippets<\/strong>, engineering best practices, and live demonstrations, you&#8217;ll see these enhancements in action and understand how to integrate them into your own systems.<\/p>\n<p>Whether you&#8217;re building your first RAG system or looking to enhance an existing one, this session will equip you with actionable insights and<span>\u00a0<\/span><strong>practical solutions<\/strong><span>\u00a0<\/span>to make your retrieval systems more robust and capable of handling real-world challenges.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_zuccoli.png\" alt=\"\"><\/p>\n<h3>Valeria Zuccoli<\/h3>\n<p>Artificial Intelligence Scientist, Bettini srl<\/p>\n<div>\n<p>Statistician by education, Valeria is an AI Scientist with a genuine passion for computer vision spec ializing in video surveillance. Today she develops real-time AI models for people and object detection, designed to prevent intrusions and enable immediate security responses. Her work tackles challenges like latency optimization and performance in dynamic settings.<\/p>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/valeria-zuccoli\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>Repetita Non Iuvant: Why Generative AI Models Cannot Feed Themselves<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example11\">Abstract<\/button><\/p>\n<div id=\"modal-example11\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">Repetita Non Iuvant: Why Generative AI Models Cannot Feed Themselves<\/h4>\n<p>As AI floods the digital landscape with content, what happens when it starts repeating itself?<br \/>This talk explores<span>\u00a0<\/span><strong>model collapse<\/strong>, a progressive erosion where<span>\u00a0<\/span><strong>LLMs<\/strong><span>\u00a0<\/span>and<span>\u00a0<\/span><strong>image generators<\/strong><span>\u00a0<\/span>loop on their own results, hindering the creation of novel output.<\/p>\n<p>We will show how self-training leads to bias and loss of diversity, examine the<span>\u00a0<\/span><strong>causes of this degradation<\/strong>, and quantify its impact on model creativity.<br \/>Finally, we will also present concrete strategies to safeguard the future of generative AI, emphasizing the critical need to preserve innovation and originality.<\/p>\n<p>By the end of this talk, attendees will gain insights into the<span>\u00a0<\/span><strong>practical implications<\/strong><span>\u00a0<\/span>of model collapse, understanding its impact on content diversity and the long-term viability of AI.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<p>        <img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/sito_foto_trinzio_lops-1.png\" alt=\"\"><\/p>\n<div>\n<p><h12 style=\"font-size: 50px; color: #ff0a6a; font-family: Manrope; font-weight: bold;\">Michelantonio Trizio<\/h12><\/p>\n<h4>Chief Technology Officer, Wideverse srl<\/h4>\n<p>Engineer &amp; Digital entrepreneur. I took the master degree in computer engineering with a thesis on AI at Polytechnic University of Bari in 2007. I worked for several years in ICT companies in Italy as a backend software developer. I attended the Mind The Bridge startup school in San Francisco in 2011. Back in Italy I started working on my own companies. Now, I&#8217;m the CTO of Wideverse, a spin-off of the Polytechnic University of Bari that works on XR and AI technologies. In addition I&#8217;m the founder and the current lead of Google Developer Group Bari community. I\u2019m a public speaker globetrotter nerd with the passion for SUP, running, Rock and photography. BBQ and IPA beers addicted.<\/p>\n<p> <a href=\"https:\/\/www.linkedin.com\/in\/michelantoniotrizio\/\" class=\"button-link\" target=\"blank\" >LinkedIn<\/a> <\/p>\n<hr \/>\n<p><h12 style=\"font-size: 50px; color: #ff0a6a; font-family: Manrope; font-weight: bold;\">Andrea Lops<\/h12><\/p>\n<h4>Software Engineer, Wideverse srl<\/h4>\n<p>Andrea Lops is a software engineer specializing in Machine Learning and software development at Wideverse, an innovative spin-off of the Polytechnic University of Bari. Currently pursuing a PhD in Electrical and Information Engineering, Andrea focuses his research on Large Language Models (LLM) and the automation of the software development life cycle, specifically in software testing. With a lot of experience in designing mobile and web solutions, Andrea has implemented technology solutions adopted by the public administration and the private sector. He has also held leadership and training roles, including managing the Google Developer Student Club at Bari Polytechnic University. Andrea is an enthusiastic advocate of digital innovation and technical education, providing consulting services in a variety of national and international settings. His passion for technology drives him to continuously explore and implement innovative solutions to real-world challenges, with an eye always on the future of artificial intelligence and software engineering.<\/p>\n<p><a href=\"https:\/\/x.com\/LopsAndrea\" class=\"button-link\" target=\"blank\">X<\/a> | <a href=\"https:\/\/www.linkedin.com\/in\/lopsandrea\/\" class=\"button-link\" target=\"blank\">LinkedIn<\/a> | <a href=\"https:\/\/github.com\/lopsandrea\" class=\"button-link\" target=\"blank\">Github<\/a><\/p>\n<\/p>\n<hr \/>\n<h3>LLM-Powered Automation for Scalable UI Testing<\/h3>\n<\/p>\n<p><button class=\"uk-button uk-button-default uk-margin-small-right\" type=\"button\" uk-toggle=\"target: #modal-example15\">Abstract<\/button><\/p>\n<div id=\"modal-example15\" uk-modal=\"\">\n<div class=\"uk-modal-dialog uk-modal-body\">\n<h4 class=\"\">LLM-Powered Automation for Scalable UI Testing<\/h4>\n<p>Automated UI testing is essential but notoriously fragile, often failing to keep pace with rapidly evolving interfaces and documentation. In this talk, we introduce a novel multi-agent architecture that leverages large language models (LLMs) to transform static documentation into dynamic, executable UI tests\u2014without writing code. Our system extracts structured user journeys from product manuals, refines them into atomic tasks using LLM agents, and executes them autonomously in live browser environments. This talk is for developers, QA engineers, and AI practitioners building or maintaining test automation pipelines in enterprise environment. Attendees will gain insights into architecting LLM-powered agents for structured extraction, and improving test resilience. We&#8217;ll explore how this system achieves high execution accuracy and adaptive self-correction, even under ambiguous or incomplete specs.<\/p>\n<p class=\"uk-text-right\"><button class=\"uk-button uk-button-default uk-modal-close\" type=\"button\">Close<\/button><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<h1>&#8230; and more to be announced!<\/h1>\n<p><img decoding=\"async\" src=\"\/2025\/wp-content\/uploads\/sites\/4\/logo_ai_big.png\" alt=\"\"><\/p>\n<p><!--more--><br \/>\n<!-- {\"type\":\"layout\",\"children\":[{\"type\":\"section\",\"props\":{\"animation\":\"slide-bottom-medium\",\"animation_delay\":\"100\",\"header_transparent\":false,\"header_transparent_text_color\":\"dark\",\"image_position\":\"center-center\",\"image_size\":\"width-1-1\",\"image_width\":\"2560\",\"media_visibility\":\"m\",\"padding\":\"large\",\"padding_remove_bottom\":false,\"padding_remove_top\":false,\"style\":\"default\",\"title_breakpoint\":\"xl\",\"title_position\":\"top-left\",\"title_rotation\":\"left\",\"vertical_align\":\"\",\"width\":\"small\"},\"children\":[{\"type\":\"row\",\"children\":[{\"type\":\"column\",\"props\":{\"image_position\":\"center-center\",\"position_sticky_breakpoint\":\"m\"},\"children\":[{\"type\":\"headline\",\"props\":{\"content\":\"AI Heroes 2025 Speakers\",\"text_align\":\"center\",\"title_element\":\"h1\",\"title_style\":\"heading-small\"}}]}],\"props\":{\"margin_remove_bottom\":true}}],\"name\":\"Hero\",\"modified\":\"2021-01-11T16:17:32.664Z\"},{\"type\":\"section\",\"props\":{\"image_position\":\"center-center\",\"padding_remove_top\":true,\"style\":\"default\",\"title_breakpoint\":\"xl\",\"title_position\":\"top-left\",\"title_rotation\":\"left\",\"vertical_align\":\"middle\",\"width\":\"default\"},\"children\":[{\"type\":\"row\",\"children\":[{\"type\":\"column\",\"props\":{\"image_position\":\"center-center\",\"position_sticky_breakpoint\":\"m\"},\"children\":[{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Peter is a Staff Developer Advocate on the Firebase at Google, helping developers build amazing experiences and high quality apps using Firebase and AI. With a passion for empowering developers and fostering innovation, Peter works tirelessly with the Firebase team to make his vision of \\u201ccutting short the time to magic\\u201d a reality. He has written code in BASIC, C, ObjectPascal, Java, Kotlin, Xtext, JavaScript, TypeScript, Objective-C, and a number of home-grown DSLs - but his all-time favourite is Swift.<\\\/p>\\n\n\n<p><a href=\\\"https:\\\/\\\/x.com\\\/peterfriese\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/peterfriese\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/github.com\\\/peterfriesee\\\" class=\\\"button-link\\\" target=\\\"blank\\\">Github<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Beyond Prompts: Building Intelligent Applications with Genkit and the Model Context Protocol<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example14\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example14\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Beyond Prompts: Building Intelligent Applications with Genkit and the Model Context Protocol<\\\/h4>\\n\n\n<p>LLMs have democratized AI, making it more accessible for everyone. But today\\u2019s chat bots still feel very disconnected. Wouldn\\u2019t it be great if you could use AI to tap into your personal knowledge and data, and use it to drive the tools you already know and love? Imagine using a chat bot to create your next pitch deck, or generating bespoke 3D scenes for your next home decoration project using inexpensive tools like Blender. In this talk, I'll show you how this is possible with tools like Genkit and MPC, the Model Context Protocol.<\\\/p>\\n\n\n<p>You will learn:<\\\/p>\\n\n\n<ul>\\n\n\n<li>What Genkit is and how its key abstractions make building AI apps easier and faster<\\\/li>\\n\n\n<li>How you can leverage MCP to allow LLMs to interact with existing apps and systems<\\\/li>\\n\n\n<li>How to architect intelligent applications that orchestrate complex tasks by connecting to and reusing your existing APIs, data sources, and specialised tools.<\\\/li>\\n<\\\/ul>\\n\n\n<p>I will even demo an agentic app built using Genkit, MCP, Swift, and Keynote that you can use to craft presentation decks using just natural language - including doing the research!<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_friese.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Staff Developer Relations Engineer, Google\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Peter Friese\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>A software architect who's been around so long he's witnessed more programming languages come and go than he can remember (20+ years, if we must count). He's built things that millions of people use daily, probably even while you're reading this. Leader of the local AWS User Group, where he tries to convince other nerds that the cloud isn't just \\\"someone else's computer.\\\" When he's not sketching architectures on bar napkins or explaining to his grandmother what a microservice is, you'll find him speaking at tech conferences, desperately trying to make the audience laugh with database jokes. His mission? Using technology to solve real-world problems, or at least that's what he tells his family to justify all the time spent in front of screens.<\\\/p>\\n\n\n<p> <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/lerro\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/github.com\\\/flerro\\\" class=\\\"button-link\\\" target=\\\"blank\\\">Github<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>How TheFork is Revolutionizing Dining Experiences with Generative AI<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example12\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example12\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">How TheFork is Revolutionizing Dining Experiences with Generative AI<\\\/h4>\\n\n\n<p>What happens when Generative AI meets the world of dining? At TheFork, we\\u2019ve transformed restaurant discovery into a personalized experience for every user. This talk will take you through our exciting journey of adopting GenAI\\u2014balancing innovation with privacy, legal compliance, and the creation of a solid AI blueprint to support multiple internal initiatives. We\\u2019ll share how we\\u2019ve leveraged diner reviews to enhance the user experience, from generating smarter recommendations to crafting personalized restaurant descriptions. Join us as we explore the challenges, lessons learned, and the strategies that are shaping TheFork into an intelligent, user-centric dining advisor. Join us as we explore the challenges, lessons learned, and the strategies that are shaping TheFork into an intelligent, user-centric dining advisor. <\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_lerro-1.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Software Architect, TheFork - TripAdvisor Group\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Francesco Lerro\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Cristiano is a Theoretical Physicist with a PhD in Quantum Information Theory from SISSA in Trieste, Italy. With over 9 years of experience in Deep Learning, he is currently the Lead AI Scientist at Pi School, working mainly on AI applied to language, space and climate challenges. He is a lecturer in Deep Learning at the Master in High-performance Computing (ICTP\\\/SISSA, Trieste) and in Quantum Machine Learning at Ca\\u2019 Foscari College School. He is the Scientific Advisor for Scientifica VC, an Italian fund investing in deep-tech startups His focus has always been on emerging technologies, AI and Quantum tech, with collaborations ranging from European Space Agency to the SIOS Remote Sensing Centre in the Svalbard Islands. In spare time he is a pilot of airplanes and gliders. He runs a newsletter on LinkedIn: Beyond Entropy.<\\\/p>\\n\n\n<p> <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/cristiano-de-nobili\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/x.com\\\/denocris\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Physics and Quantum Inspired AI<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example20\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example20\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Physics and Quantum Inspired AI<\\\/h4>\\n\n\n<p>This 30-minute talk will motivate and introduce Physics and Quantum methods that will improve current machine learning algorithms and perhaps help solve the growing energy demands of LLMs. Starting from Landauer's principle, we will discuss the limitations of current semiconductor technologies and how emerging computing paradigms could power future training and inference. <\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_denobili.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Freelance Lead Scientist & Scientific Advisor\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Cristiano De Nobili\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>I am the co-founder of Clearbox AI, a company specializing in synthetic data generation solutions to drive innovation and enhance data privacy. I've lived for more than 10 years in the Netherlands where I got my PhD in applied sciences and worked as a scientific software developer. \\n\\nOutside of work, I enjoy hiking in the beautiful Piedmontese mountains. I'm also passionate about farming, with a special interest in experimenting with hydroponic techniques.<\\\/p>\\n\n\n<p> <a href=\\\"https:\\\/\\\/x.com\\\/virgillus\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/luca-gilli\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/github.com\\\/gillus\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Replica Italia: how to build a digital twin of the Italian population<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example23\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example23\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Replica Italia: how to build a digital twin of the Italian population<\\\/h4>\\n\n\n<p>Replica Italia is a synthetic, privacy-safe digital twin of the Italian population. This presentation explores the technical challenges and data sources involved in its development.\\u200b\\nCreating a digital twin required integrating diverse datasets: we utilised open data, statistical modelling, and simulations to represent demographic, behavioural, and geolocation attributes. Key data sources included public demographic statistics, consumer behaviour studies, and geospatial information.\\u200b The resulting platform provides instant access to AI-generated panels of over 60 million synthetic Italian users, facilitating concept testing, surveys, and consumer response simulations. It also enables the enrichment of customer profiles and the creation of high-quality synthetic audiences for targeted advertising, all without accessing personal data. \\nThis talk provides an in-depth exploration of the methodologies employed to integrate diverse data sources in creating a national-scale digital twin.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_gilli.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"CTO, Clearbox AI\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Luca Gilli\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>I'm a Software Engineer specialized in AI and Computer Vision, with a strong background in web and AI technologies. Over the past two years, I've focused on building GenAI applications\\u2014working with LLMs, RAG, and AI agents.<\\\/p>\\n\n\n<p>I'm the co-founder and CTO of three companies:<\\\/p>\\n\n\n<ul>\\n\n\n<li><strong>M\\u00f2nade<\\\/strong>, a 30-person consultancy delivering custom software and AI Agents<\\\/li>\\n\n\n<li><strong>Elf Games<\\\/strong>, a game studio with two internationally recognized titles<\\\/li>\\n\n\n<li><strong>Elysia<\\\/strong>, a SaaS platform that helps companies unlock internal knowledge using Generative AI<\\\/li>\\n<\\\/ul>\\n\n\n<p><a href=\\\"https:\\\/\\\/x.com\\\/ProGiEmmeh\\\" target=\\\"blank\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/piero-dotti\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/github.com\\\/ProGM\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Scaling Vector Search with PostgreSQL: A Deep Dive into pgvector Optimization<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example24\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example24\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Scaling Vector Search with PostgreSQL: A Deep Dive into pgvector Optimization<\\\/h4>\\n\n\n<p><strong>Are you building AI applications that need a reliable, scalable vector store? This talk provides a comprehensive guide to configuring PostgreSQL as an optimal vector store for AI applications<\\\/strong><span>\\u00a0<\\\/span>using the pgvector extension.<\\\/p>\\n\n\n<p>We'll begin with a brief introduction to vector stores and PostgreSQL fundamentals before diving into the pgvector extension and its capabilities. The presentation will explore essential vector operations and compare indexing approaches (<strong>HNSW vs. IVFFlat<\\\/strong>), offering practical guidance on hyperparameter tuning for your specific use cases.<\\\/p>\\n\n\n<p>We'll also cover advanced optimization techniques including:<\\\/p>\\n\n\n<ul>\\n\n\n<li>Reduced precision<\\\/li>\\n\n\n<li>Quantization methods<\\\/li>\\n\n\n<li>Various scaling strategies such as partitioning, sharding, and replication to handle growing data volumes<\\\/li>\\n<\\\/ul>\\n\n\n<p>We'll also see a real-world example of a semantic search application using pgvector, demonstrating how to implement and optimize it for production.<\\\/p>\\n\n\n<p><strong>Whether you're implementing semantic search, recommendation systems, or other vector-based AI applications, you'll leave with actionable knowledge to configure PostgreSQL as a high-performance, production-ready vector database.<\\\/strong><\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_dotti.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"CTO, Monade srl\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Piero Dotti\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<h12 style=\\\"font-size: 50px; color: #ff0a6a; font-family: Manrope; font-weight: bold;\\\">Andrea Caglio<\\\/h12><\\\/p>\\n\n\n<h4>AI & Software Engineer, Intr\\u00e9 srl | Memoria <\\\/h4>\\n\n\n<p>I am a software & AI engineer with a strong passion for Artificial Intelligence and Machine Learning. At Intr\\u00e9, I played a key role in the creation of Memoria, the business unit dedicated to developing tailored AI solutions. Here, I focus on building innovative AI applications that address real-world challenges.\\n\\nBeyond development, I believe in knowledge sharing: I enjoy showcasing what AI can achieve today, which is why I frequently speak at conferences, sharing practical experiences and use cases.<\\\/p>\\n <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/andrea-caglio\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\" >LinkedIn<\\\/a> \\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h12 style=\\\"font-size: 50px; color: #ff0a6a; font-family: Manrope; font-weight: bold;\\\">Luca Pozzoli<\\\/h12><\\\/p>\\n\n\n<h4>Software & AI Engineer, Intr\\u00e9 srl | Memoria <\\\/h4>\\n\n\n<p>My academic path allowed me to obtain a master's degree in mathematics, while my working career led me to coding.\\nCurrently working as an AI & software engineer, I focus on building AI solutions: starting from the prototype, features are added incrementally to build the final product. I like comparing this to the work of a craftsman, who keeps on refining and improving its own work.\\nWhat else? In my spare time I like watching movies, listening to music and playing boardgames.<\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Back to the Prompt: Rewriting the Future of AI with Real-Time Knowledge<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example25\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example25\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Back to the Prompt: Rewriting the Future of AI with Real-Time Knowledge<\\\/h4>\\n\n\n<p>What if your AI assistant could travel through time, rewriting the rules of documentation as it goes?\\nIn this talk, we\\u2019ll take you on a journey to the future of knowledge management, where your assistant doesn't rely on outdated documents. Instead, it can ingest real-time information via chat, making sure that this new data takes priority over the old. Powered by cutting-edge Generative AI, LLMs, Bots, and a Retrieval-Augmented Generation (RAG) architecture, our system is capable of time-traveling knowledge, collecting, structuring, and storing it as the ultimate source of truth.\\n\\nWe\\u2019ll dive into the research and technical architecture that made it possible, exploring how we integrate dynamic knowledge injection, prioritize real-time inputs, and maintain consistency across the system. You\\u2019ll learn how we built an AI assistant that adapts to evolving needs without compromising on reliability or user experience.\\n\\nSo, buckle up! We\\u2019re about to take your AI into the present. No flux capacitor required!\\n\\nTarget audience: developers, ML engineers, product managers.\\n    \\n    <\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_caglio-pozzoli.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>I'm an electronic engineer who has been working in IT Innovation since the last 30 years at international level.\\nI had the luxury to ride the internet, mobility and digital revolutions. Since 5 years I look after AI in Customer Experience and recently took the responsibility of being an AI Sales for the south EMEA countries at Cisco Systems.<\\\/p>\\n\n\n<p> <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/massimilianocaranzano\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> <\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Internet of Agents: the role of the network in the AI revolution<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example21\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example21\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Internet of Agents: the role of the network in the AI revolution<\\\/h4>\\n\n\n<p>We are in the AI Agentic phase, where AI entities are able to autonomously reason and act (ReAct) and this will literally change the way we Live, Play and Work.  A new army of Autonomous Digital Workes will join the humans at work as well as in private life changing the entire IT industry: software, hardware, infrastructure and services. This moltitude of digital resources will require a new \\\"internet\\\" working differently, al layer 7, able to Connect, Secure, Observe and foster Collaboration exactly as it was in the beginning of the internet revolution. We are at the dawn of the IOA, Internet of Agents.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_caranzano.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Artificial Intelligence Account Executive EMEA South, Cisco Systems\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Massimiliano Caranzano\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Davide is a seasoned software engineer and co-founder of Volcanic Minds, a digital experience company based in Turin. With 15+ years of experience, he has led the development of complex web and mobile applications using mainly JavaScript and Node.js. Previously CTO at epiCura, he helped scale the healthtech platform from startup to national growth. He brings deep expertise in frontend engineering, architecture, and team leadership. Passionate about building tech that solves real problems, Davide now focuses on high-impact digital products for startups and brands. He\\u2019s also a keen photographer and metal guitarist. At this event, he\\u2019ll share lessons from his journey bridging product vision and engineering execution.<\\\/p>\\n\n\n<p><a href=\\\"https:\\\/\\\/x.com\\\/DDVolcanicMinds\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/davidedispenza\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Agent Collaboration Across Frameworks: Interoperability with CrewAI, LangGraph, and Google A2A<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example26\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example26\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Agent Collaboration Across Frameworks: Interoperability with CrewAI, LangGraph, and Google A2A<\\\/h4>\\n\n\n<p>Modern AI development is rapidly shifting from isolated LLM prompts to orchestrated systems of collaborative agents. But with so many tools and frameworks emerging, interoperability remains a key challenge. In this talk, we introduce three powerful and complementary technologies: CrewAI, a lightweight framework for autonomous multi-agent collaboration; LangGraph, a graph-based orchestration engine for LLM workflows; and Google\\u2019s Agent-to-Agent (A2A) protocol, a new open standard enabling agents to discover and communicate across frameworks and infrastructures.<\\\/p>\\n\n\n<p>You\\u2019ll learn how each technology works, what problems they solve, and how they differ in design and application. The final part of the talk is a live demo: an AI agent that receives a user request and coordinates with two separate agent stacks\\u2014one built with CrewAI and another with LangGraph\\u2014via the Google A2A protocol, showcasing seamless cross-framework problem-solving in action.<\\\/p>\\n\n\n<p>Audience: AI developers, architects, and technical leads building agent-based systems or evaluating agent frameworks. Length: 40 minutes. Innovation: This is a brand-new talk featuring a live demo of multi-framework agent interoperability using Google A2A. Takeaways: Attendees will leave with a clear understanding of CrewAI, LangGraph, and A2A; practical insights on when and how to use each; and a blueprint for building scalable, interoperable, multi-agent systems.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_dispenza.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"CTO, Volcanic Minds\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Davide Dispenza\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Hi, I\\u2019m Daniele - I\\u2019m a Head of Engineering with 15+ years of experience in backend development and DevOps \\u2014 mostly in Java, but I\\u2019ve been having a lot of fun with Node.js over the past couple of years. I\\u2019ve led teams through complex challenges, building scalable systems and navigating fast-changing environments. Over the years, I\\u2019ve seen it all: unexpected pivots, hard-won victories, and plenty of tricky problems. My approach is simple \\u2014 identify areas for growth, anticipate change before it hits, and solve problems at the root so they stay solved. I\\u2019m passionate about team culture. I thrive in collaborative environments where people feel empowered to do their best work. I bring strong analytical skills to the table \\u2014 but I\\u2019m also very aware I don\\u2019t know everything (and that\\u2019s half the fun). I believe the journey matters just as much as the outcome. I\\u2019m endlessly curious and love working with people from different backgrounds. I see diversity as a source of creativity \\u2014 and I\\u2019m always up for exploring new ideas, especially when they challenge how we build software.<\\\/p>\\n\n\n<p><a href=\\\"https:\\\/\\\/x.com\\\/daniele_ntn\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/danieleantonini\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/github.com\\\/dantonini\\\/user-story-matrix\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">Github<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Coding with AI: How to Get Predictable Results <\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example28\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example28\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Coding with AI: How to Get Predictable Results<\\\/h4>\\n\n\n<p>AI coding assistants like Copilot, ChatGPT, and Cursor have transformed how we write software \\u2014 but often in unpredictable ways. Vague prompts, inconsistent results, and scattered workflows are now part of our daily reality. The promise of AI-powered development is huge, but without structure, it's easy to fall into chaos.\\n\\nIn this talk, I\\u2019ll introduce User Story Matrix (USM) \\u2014 an open-source CLI tool that helps developers orchestrate AI-assisted development with clarity and control. USM lets you define structured user stories, generate implementation blueprints, and guide AI tools through testable, repeatable steps.\\nWhether you're working solo or in a team, USM gives you a lightweight, developer-first workflow to make AI coding deliberate and scalable \\u2014 not just experimental.\\nThis talk is aimed at developers, tech leads, and AI tool builders looking to reduce noise and get real results from AI coding. You\\u2019ll walk away with a fresh mindset, a practical CLI demo, and a repeatable process to bring predictability back to your AI-assisted workflow.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_antonini.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Head of Engineering,  Translated\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Daniele Antonini\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Chief Product & Technology Officer, driving innovation through strategic product vision and cutting-edge AI solutions. \\nStartup Co-founder and Strategic Advisor, with 20+ years of experience in creating impactful, data-driven technologies.\\nPhD in AI, Professor, Editorial Board Member and Author of 100+ scientific publications and 3 books. \\nPassionate about using technology to solve complex challenges and shape a smarter, more connected future.<\\\/p>\\n\n\n<p> <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/giovanni-cugliari-333b6664\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> <\\\/p>\\n\\n\n\n<hr \\\/>\\n\n\n<h3>The composite AI-product stack: Building intelligent systems with agents and generative AI\\n<\\\/h3>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example18\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example18\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">The composite AI-product stack: Building intelligent systems with agents and generative AI\\n<\\\/h4>\\n\n\n<p>As individuals and organizations strive to make smarter, faster decisions, AI is evolving beyond prediction into a new era of causal, intelligent, and collaborative decision-making. This session explores how developers can build cutting-edge Decision Intelligence Platforms by combining three key technologies. First, we'll look at how graph analytics uncover causal relationships in data, revealing patterns and dependencies that power smarter insights. Next, we'll dive into a simulation engine that enables scalable scenario planning, helping teams test \\u201cwhat-if\\u201d situations before acting. Finally, we\\u2019ll explore generative data storytelling and an alerting and recommendation system that transforms raw data into meaningful, real-time narratives and guidance. Together, these elements create a platform that doesn\\u2019t just react to data\\u2014but understands it, plans around it, and collaborates with users to make proactive decisions.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_cugliari.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"CPTO, Vedrai\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Giovanni Cugliari\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Benedetto is a Computer Engineer with a strong background in software development and a deep focus on Artificial Intelligence. He holds a Master\\u2019s degree in Computer Engineering with a specialization in Data Science &amp; AI from Politecnico di Torino, where he developed a solid foundation in machine learning, data processing, and intelligent systems. He currently works as an AI Engineer at Datapizza, where he helps companies unlock the value of Generative AI by designing and building production-ready solutions, collaborating with an exceptional team of talented engineers and AI experts to bring ideas from prototype to production. Over the past year, he has led the development of multi-agent chatbots in enterprise environments, combining LLMs, advanced RAG strategies and powerful evaluation pipelines to deliver real-world impact.<\\\/p>\\n\n\n<p><a href=\\\"https:\\\/\\\/x.com\\\/benemana?s=21&amp;t=l_pFIGFkUOFd1JTtZz_bvA\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/bdtmns\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>How to (not) fail a GenAI project: practical lessons and technical insights from building and evolving Multi-Agent Chatbots in production<\\\/h3>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example19\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example19\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">How to (not) fail a GenAI project: practical lessons and technical insights from building and evolving Multi-Agent Chatbots in production<\\\/h4>\\n\n\n<p>Why do even successful GenAI projects often plateau after reaching production? Moving from PoC to a live system is only the beginning \\u2014 the real challenge lies in scaling it, making it <strong>trustworthy<\\\/strong>, and\\u00a0 <strong>continuously improving<\\\/strong> its impact. Whether you\\u2019re navigating your first demo or already running a GenAI solution in production, this talk is for you. Here I\\u2019ll share hard-earned lessons from building production-grade <strong>multi-agent chatbots <\\\/strong>(e.g. \\u201ctalk-with-your-documents\\u201d) in a corporate environment \\u2014 lessons grounded in hands-on experience, packed with <strong>practical tips <\\\/strong>and references to GenAI <strong>tools and frameworks <\\\/strong>that actually work. We\\u2019ll cover:<\\\/p>\\n\n\n<ul>\\n\n\n<li>why involving business stakeholders <strong>early and often <\\\/strong>is not just a nice-to-have, but a critical success factor \\u2014 and <em>how to do it<\\\/em>.<\\\/li>\\n\n\n<li>How to build robust <strong>evaluation pipelines <\\\/strong>using real user data and expert input to assess relevance, accuracy, and overall system performance <em>over time<\\\/em>.<\\\/li>\\n\n\n<li>How to strike the <em>right balance<\\\/em> between elegant simplicity and complex <strong>agents architectures<\\\/strong>, with a focus on composable <strong>patterns <\\\/strong>\\u00a0and <strong>advanced strategies for RAG <\\\/strong>(chunking, pre-retrieval, post-retrieval, and more).<\\\/li>\\n\n\n<li>The main challenges of\\u00a0 <em>unstructured data<\\\/em> \\u2014 and how\\u00a0<strong>smart preprocessing <\\\/strong>can be helpful in compensating for poor document quality.<\\\/li>\\n\n\n<li><strong>Post-deployment <\\\/strong>strategies: onboarding users, increasing trust through <strong>transparency <\\\/strong>(think interactive source tracing and agent flow visualization), and iterating based on <strong>real-world queries and feedback.<\\\/strong>\\u00a0<\\\/li>\\n<\\\/ul>\\n\n\n<p>This is a new, original talk for AI Heroes, aimed at developers, AI engineers, and product teams building GenAI solutions. Get ready for a session filled with hands-on advice and real-world lessons learned from taking GenAI projects to production across a variety of contexts and scenarios.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_manasseri.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"AI Engineer, Datapizza\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Benedetto Manasseri\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Emanuele is an engineer, researcher, and entrepreneur with a passion for artificial intelligence. He earned his PhD by exploring time series forecasting in the energy sector and spent time as a guest researcher at EPFL in Lausanne. Today, he is co-founder and Head of AI at xtream, a boutique company that applies cutting-edge technology to solve complex business challenges. Emanuele is also a contract professor in AI at the Catholic University of Milan. He has published eight papers in international journals and contributed to over 30 international conferences worldwide. His engagements include AMLD Lausanne, ODSC London, WeAreDevelopers Berlin, PyData Berlin, PyData Paris, PyCon Florence, the Swiss Python Summit in Zurich, and Codemotion Milan. Emanuele has been a guest lecturer at Italian, Swiss, and Polish universities.<\\\/p>\\n\n\n<p><a href=\\\"https:\\\/\\\/x.com\\\/donlelef\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/emanuelefabbiani\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\" >LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/github.com\\\/donlelef\\\" class=\\\"button-link\\\" target=\\\"blank\\\" >Github<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Beyond Basic RAG: HyDE, Visual Embeddings, and Other Tricks<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example17\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example17\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Beyond Basic RAG: HyDE, Visual Embeddings, and Other Tricks<\\\/h4>\\n\n\n<p>The foundational<span>\\u00a0<\\\/span><strong>RAG architecture<\\\/strong><span>\\u00a0<\\\/span>we all know - built on embeddings, vector databases, retrieval algorithms, and generative models - served us well in 2023. Now it's time to explore the powerful enhancements that have emerged to take RAG to the next level.<\\\/p>\\n\n\n<p>We'll explore<span>\\u00a0<\\\/span><strong>HyDE<\\\/strong>, an approach that leverages an LLM to generate hypothetical documents, creating a stronger bridge between user queries and relevant content. The result is a marked improvement in retrieval accuracy without requiring additional models.<\\\/p>\\n\n\n<p><strong>Visual content handling<\\\/strong><span>\\u00a0<\\\/span>gets a major upgrade through advanced embedding techniques, particularly with the introduction of<span>\\u00a0<\\\/span><strong>ColPali<\\\/strong>. This retrieval model works directly with document images, using vision-language models to create rich, contextual embeddings from document pages. It's particularly powerful when dealing with PDFs, scanned documents, and other visually structured content that traditional RAG systems struggle with.<\\\/p>\\n\n\n<p>For those focused on efficiency, we'll examine<span>\\u00a0<\\\/span><strong>SPLADE<\\\/strong>, a neural retrieval model that creates sparse representations of both documents and queries. By combining the speed advantages of traditional inverted indexes with the accuracy of modern neural approaches, SPLADE offers a compelling solution for production environments.<\\\/p>\\n\n\n<p>The discussion isn't just theoretical - we'll ground everything in practical implementation. Through<span>\\u00a0<\\\/span><strong>code snippets<\\\/strong>, engineering best practices, and live demonstrations, you'll see these enhancements in action and understand how to integrate them into your own systems.<\\\/p>\\n\n\n<p>Whether you're building your first RAG system or looking to enhance an existing one, this session will equip you with actionable insights and<span>\\u00a0<\\\/span><strong>practical solutions<\\\/strong><span>\\u00a0<\\\/span>to make your retrieval systems more robust and capable of handling real-world challenges.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_fabbiani.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Head of AI, xtream\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Emanuele Fabbiani\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Catalin Hanga (PhD) is a Data Scientist, currently working at the Open Innovation AI Lab of Iveco Group in Switzerland. His main professional focus is on research and development of advanced machine learning algorithms for solving technical problems in the automotive industry. His recent projects include designing a documentation search chatbot based on Retrieval Augmented Generation, as well as implementing autonomous LLM agents with function calling and tool usage. Prior to this, he briefly worked in a similar role for a startup in the insurtech industry. He has obtained a PhD in Mathematics from the University of York, UK, and holds an M.Sc. in Physics from the University of Bucharest, Romania. During his M.Sc. studies, he also worked as a researcher at CERN in Geneva, Switzerland, analysing experimental data collected by the detectors of the Large Hadron Collider. He is regularly giving public talks on technical topics at various Data Science and AI conferences.<\\\/p>\\n\n\n<p> <a href=\\\"www.linkedin.com\\\/in\\\/catalin-hanga-phd-3046b3198\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> | <a href=\\\"www.github.com\\\/catalin-hanga\\\" class=\\\"button-link\\\" target=\\\"blank\\\">Github<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>The Rise of Autonomous Agents in the Era of Generative AI<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example17\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example17\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">The Rise of Autonomous Agents in the Era of Generative AI<\\\/h4>\\n\n\n<p>Generative AI and LLM applications have recently started to advance beyond simple question-answering and basic text summarization tasks. The next frontier in NLP lies in harnessing these technologies to create autonomous agents - systems capable of reasoning, planning, and executing complex sequences of actions with minimal human intervention. This talk will explore the principles and challenges of designing such agents, focusing on how LLMs can function as core components for decision-making and goal-oriented planning. We will review strategies for integrating LLMs with external tools, APIs, and feedback loops, with the purpose of enabling adaptive behaviour in dynamic environments. We will also highlight real-world applications, from task orchestration and code generation to multi-agent collaborative workflows. Whether you're an AI enthusiast, developer, or researcher, this session will provide a roadmap for navigating this exciting domain of truly intelligent AI-driven automation. <\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_hanga.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Data Scientist, Iveco Group\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"status\":\"disabled\",\"title\":\"Catalin Hanga\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Statistician by education, Valeria is an AI Scientist with a genuine passion for computer vision spec ializing in video surveillance. Today she develops real-time AI models for people and object detection, designed to prevent intrusions and enable immediate security responses. Her work tackles challenges like latency optimization and performance in dynamic settings.<\\\/p>\\n\n\n<p><a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/valeria-zuccoli\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Repetita Non Iuvant: Why Generative AI Models Cannot Feed Themselves<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example11\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example11\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Repetita Non Iuvant: Why Generative AI Models Cannot Feed Themselves<\\\/h4>\\n\n\n<p>As AI floods the digital landscape with content, what happens when it starts repeating itself?<br \\\/>This talk explores<span>\\u00a0<\\\/span><strong>model collapse<\\\/strong>, a progressive erosion where<span>\\u00a0<\\\/span><strong>LLMs<\\\/strong><span>\\u00a0<\\\/span>and<span>\\u00a0<\\\/span><strong>image generators<\\\/strong><span>\\u00a0<\\\/span>loop on their own results, hindering the creation of novel output.<\\\/p>\\n\n\n<p>We will show how self-training leads to bias and loss of diversity, examine the<span>\\u00a0<\\\/span><strong>causes of this degradation<\\\/strong>, and quantify its impact on model creativity.<br \\\/>Finally, we will also present concrete strategies to safeguard the future of generative AI, emphasizing the critical need to preserve innovation and originality.<\\\/p>\\n\n\n<p>By the end of this talk, attendees will gain insights into the<span>\\u00a0<\\\/span><strong>practical implications<\\\/strong><span>\\u00a0<\\\/span>of model collapse, understanding its impact on content diversity and the long-term viability of AI.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_zuccoli.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Artificial Intelligence Scientist, Bettini srl\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"Valeria Zuccoli\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"},{\"type\":\"panel\",\"props\":{\"content\":\"\\n\n\n<h12 style=\\\"font-size: 50px; color: #ff0a6a; font-family: Manrope; font-weight: bold;\\\">Michelantonio Trizio<\\\/h12><\\\/p>\\n\n\n<h4>Chief Technology Officer, Wideverse srl<\\\/h4>\\n\n\n<p>Engineer &amp; Digital entrepreneur. I took the master degree in computer engineering with a thesis on AI at Polytechnic University of Bari in 2007. I worked for several years in ICT companies in Italy as a backend software developer. I attended the Mind The Bridge startup school in San Francisco in 2011. Back in Italy I started working on my own companies. Now, I'm the CTO of Wideverse, a spin-off of the Polytechnic University of Bari that works on XR and AI technologies. In addition I'm the founder and the current lead of Google Developer Group Bari community. I\\u2019m a public speaker globetrotter nerd with the passion for SUP, running, Rock and photography. BBQ and IPA beers addicted.<\\\/p>\\n <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/michelantoniotrizio\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\" >LinkedIn<\\\/a> \\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h12 style=\\\"font-size: 50px; color: #ff0a6a; font-family: Manrope; font-weight: bold;\\\">Andrea Lops<\\\/h12><\\\/p>\\n\n\n<h4>Software Engineer, Wideverse srl<\\\/h4>\\n\n\n<p>Andrea Lops is a software engineer specializing in Machine Learning and software development at Wideverse, an innovative spin-off of the Polytechnic University of Bari. Currently pursuing a PhD in Electrical and Information Engineering, Andrea focuses his research on Large Language Models (LLM) and the automation of the software development life cycle, specifically in software testing. With a lot of experience in designing mobile and web solutions, Andrea has implemented technology solutions adopted by the public administration and the private sector. He has also held leadership and training roles, including managing the Google Developer Student Club at Bari Polytechnic University. Andrea is an enthusiastic advocate of digital innovation and technical education, providing consulting services in a variety of national and international settings. His passion for technology drives him to continuously explore and implement innovative solutions to real-world challenges, with an eye always on the future of artificial intelligence and software engineering.<\\\/p>\\n\n\n<p><a href=\\\"https:\\\/\\\/x.com\\\/LopsAndrea\\\" class=\\\"button-link\\\" target=\\\"blank\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/lopsandrea\\\/\\\" class=\\\"button-link\\\" target=\\\"blank\\\">LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/github.com\\\/lopsandrea\\\" class=\\\"button-link\\\" target=\\\"blank\\\">Github<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>LLM-Powered Automation for Scalable UI Testing<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example15\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example15\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">LLM-Powered Automation for Scalable UI Testing<\\\/h4>\\n\n\n<p>Automated UI testing is essential but notoriously fragile, often failing to keep pace with rapidly evolving interfaces and documentation. In this talk, we introduce a novel multi-agent architecture that leverages large language models (LLMs) to transform static documentation into dynamic, executable UI tests\\u2014without writing code. Our system extracts structured user journeys from product manuals, refines them into atomic tasks using LLM agents, and executes them autonomously in live browser environments. This talk is for developers, QA engineers, and AI practitioners building or maintaining test automation pipelines in enterprise environment. Attendees will gain insights into architecting LLM-powered agents for structured extraction, and improving test resilience. We'll explore how this system achieves high execution accuracy and adaptive self-correction, even under ambiguous or incomplete specs.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_trinzio_lops-1.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"title\":\"\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"}]}]}]},{\"type\":\"section\",\"props\":{\"image_position\":\"center-center\",\"style\":\"default\",\"title_breakpoint\":\"xl\",\"title_position\":\"top-left\",\"title_rotation\":\"left\",\"vertical_align\":\"middle\",\"width\":\"default\"},\"children\":[{\"type\":\"row\",\"props\":{\"layout\":\"4-5,1-5\"},\"children\":[{\"type\":\"column\",\"props\":{\"image_position\":\"center-center\",\"position_sticky_breakpoint\":\"m\",\"width_medium\":\"4-5\"},\"children\":[{\"type\":\"headline\",\"props\":{\"content\":\"... and more to be announced!\",\"text_align\":\"left\",\"title_element\":\"h1\",\"title_style\":\"heading-small\"}},{\"type\":\"panel\",\"props\":{\"content\":\"\n\n<p>Jessica Randall is an Android Developer and tech co-lead at Mentorlst, specializing in Jetpack Compose. She holds a Master's degree in Mathematics, where she applied data science and Topological Data Analysis to complex societal challenges. A passionate advocate for women in STEM, Jessica has held leadership roles as a Women TechMaker Ambassador, GDSC Alumni Lead, and Girl Code Ambassador. As a co-organizer of GDG Cape Town, she fosters growth in the local developer community. Her interest in AI and Machine Learning, sparked through Google Crowdsource, drives her continuous learning and innovation in the tech space.<\\\/p>\\n\n\n<p> <a href=\\\"https:\\\/\\\/x.com\\\/JustJessZA\\\" class=\\\"button-link\\\">X<\\\/a> | <a href=\\\"https:\\\/\\\/www.linkedin.com\\\/in\\\/jessica-randall-293ab9205\\\/\\\" class=\\\"button-link\\\">LinkedIn<\\\/a> | <a href=\\\"https:\\\/\\\/github.com\\\/Starchild13\\\" class=\\\"button-link\\\">Github<\\\/a><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<hr \\\/>\\n\n\n<h3>Prompt Engineering Meets Kotlin: Building Conversational AI for Android<\\\/h3>\\n\n\n<p><\\\/p>\\n\n\n<p><\\\/p>\\n\n\n<p><button class=\\\"uk-button uk-button-default uk-margin-small-right\\\" type=\\\"button\\\" uk-toggle=\\\"target: #modal-example13\\\">Abstract<\\\/button><\\\/p>\\n\n\n<div id=\\\"modal-example13\\\" uk-modal=\\\"\\\">\\n\n\n<div class=\\\"uk-modal-dialog uk-modal-body\\\">\\n\n\n<h4 class=\\\"\\\">Prompt Engineering Meets Kotlin: Building Conversational AI for Android<\\\/h4>\\n\n\n<p>Discover how Kotlin empowers developers to integrate AI-driven conversational experiences into Android applications. This talk delves into a case study where prompt engineering techniques are used to create an interactive vocabulary-learning assistant modeled after a spelling bee champion. The assistant generates definitions, synonyms, etymology, pronunciations, and contextual sentences through intelligent prompts and Kotlin-based implementation. Attendees will learn how Kotlin simplifies API interactions and leverages coroutines for efficient asynchronous processing. Key takeaways include designing AI-powered features, integrating conversational AI with Kotlin, and delivering seamless, user-focused applications. Ideal for developers seeking practical insights into AI and mobile innovation.<\\\/p>\\n\n\n<p class=\\\"uk-text-right\\\"><button class=\\\"uk-button uk-button-default uk-modal-close\\\" type=\\\"button\\\">Close<\\\/button><\\\/p>\\n<\\\/div>\\n<\\\/div>\",\"content_column_breakpoint\":\"m\",\"content_margin\":\"small\",\"height_expand\":true,\"icon_width\":80,\"id\":\"speakers-emily-jeffreys\",\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/sito_foto_randall.png\",\"image_align\":\"left\",\"image_grid_breakpoint\":\"s\",\"image_grid_column_gap\":\"collapse\",\"image_grid_row_gap\":\"collapse\",\"image_grid_width\":\"1-3\",\"image_svg_color\":\"emphasis\",\"link_style\":\"default\",\"link_target\":false,\"link_text\":\"Read more\",\"margin\":\"default\",\"meta\":\"Android Co-Lead, Mentorlst\",\"meta_align\":\"below-title\",\"meta_element\":\"div\",\"meta_margin\":\"small\",\"meta_style\":\"h3\",\"panel_expand\":\"image\",\"panel_image_no_padding\":true,\"panel_padding\":\"default\",\"panel_style\":\"card-default\",\"status\":\"disabled\",\"title\":\"Jessica H Randall\",\"title_align\":\"top\",\"title_color\":\"primary\",\"title_element\":\"h3\",\"title_grid_breakpoint\":\"m\",\"title_grid_width\":\"1-2\",\"title_hover_style\":\"reset\",\"title_style\":\"heading-medium\"},\"name\":\"speakers_panel\"}]},{\"type\":\"column\",\"props\":{\"image_position\":\"center-center\",\"position_sticky_breakpoint\":\"m\",\"width_medium\":\"1-5\"},\"children\":[{\"type\":\"image\",\"props\":{\"image\":\"wp-content\\\/uploads\\\/sites\\\/4\\\/logo_ai_big.png\",\"image_height\":100,\"image_svg_color\":\"emphasis\",\"margin\":\"default\"}}]}]}]}],\"version\":\"4.5.13\"} --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>AI Heroes 2025 Speakers Peter Friese Staff Developer Relations Engineer, Google Peter is a Staff Developer Advocate on the Firebase at Google, helping developers build amazing experiences and high quality apps using Firebase and AI. With a passion for empowering developers and fostering innovation, Peter works tirelessly with the Firebase team to make his vision [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":5229,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-5292","page","type-page","status-publish","has-post-thumbnail","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Speakers - AI Heroes 2025<\/title>\n<meta name=\"description\" content=\"All the speakers of AI Heroes the annual AI conference in person in Turin, Italy, featuring international speakers and sponsors\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/aiheroes.it\/2025\/speakers\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Speakers - AI Heroes 2025\" \/>\n<meta property=\"og:description\" content=\"All the speakers of AI Heroes the annual AI conference in person in Turin, Italy, featuring international speakers and sponsors\" \/>\n<meta property=\"og:url\" content=\"https:\/\/aiheroes.it\/2025\/speakers\/\" \/>\n<meta property=\"og:site_name\" content=\"AI Heroes 2025\" \/>\n<meta property=\"article:modified_time\" content=\"2025-05-26T08:35:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/aiheroes.it\/2025\/wp-content\/uploads\/sites\/4\/live.png\" \/>\n\t<meta property=\"og:image:width\" content=\"220\" \/>\n\t<meta property=\"og:image:height\" content=\"220\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@ai_heroes\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/speakers\\\/\",\"url\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/speakers\\\/\",\"name\":\"Speakers - AI Heroes 2025\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/speakers\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/speakers\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/live.png\",\"datePublished\":\"2025-04-09T08:32:19+00:00\",\"dateModified\":\"2025-05-26T08:35:30+00:00\",\"description\":\"All the speakers of AI Heroes the annual AI conference in person in Turin, Italy, featuring international speakers and sponsors\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/speakers\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/aiheroes.it\\\/2025\\\/speakers\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/speakers\\\/#primaryimage\",\"url\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/live.png\",\"contentUrl\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/live.png\",\"width\":220,\"height\":220},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/speakers\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Speakers\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/#website\",\"url\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/\",\"name\":\"AI Heroes 2025\",\"description\":\"Artificial Intelligence conference\",\"publisher\":{\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/#organization\",\"name\":\"Synesthesia Events\",\"url\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/logo_AIHeroes.png\",\"contentUrl\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/logo_AIHeroes.png\",\"width\":1080,\"height\":364,\"caption\":\"Synesthesia Events\"},\"image\":{\"@id\":\"https:\\\/\\\/aiheroes.it\\\/2025\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/ai_heroes\",\"https:\\\/\\\/www.linkedin.com\\\/showcase\\\/aiheroes-it\\\/\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Speakers - AI Heroes 2025","description":"All the speakers of AI Heroes the annual AI conference in person in Turin, Italy, featuring international speakers and sponsors","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/aiheroes.it\/2025\/speakers\/","og_locale":"en_US","og_type":"article","og_title":"Speakers - AI Heroes 2025","og_description":"All the speakers of AI Heroes the annual AI conference in person in Turin, Italy, featuring international speakers and sponsors","og_url":"https:\/\/aiheroes.it\/2025\/speakers\/","og_site_name":"AI Heroes 2025","article_modified_time":"2025-05-26T08:35:30+00:00","og_image":[{"width":220,"height":220,"url":"https:\/\/aiheroes.it\/2025\/wp-content\/uploads\/sites\/4\/live.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_site":"@ai_heroes","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/aiheroes.it\/2025\/speakers\/","url":"https:\/\/aiheroes.it\/2025\/speakers\/","name":"Speakers - AI Heroes 2025","isPartOf":{"@id":"https:\/\/aiheroes.it\/2025\/#website"},"primaryImageOfPage":{"@id":"https:\/\/aiheroes.it\/2025\/speakers\/#primaryimage"},"image":{"@id":"https:\/\/aiheroes.it\/2025\/speakers\/#primaryimage"},"thumbnailUrl":"https:\/\/aiheroes.it\/2025\/wp-content\/uploads\/sites\/4\/live.png","datePublished":"2025-04-09T08:32:19+00:00","dateModified":"2025-05-26T08:35:30+00:00","description":"All the speakers of AI Heroes the annual AI conference in person in Turin, Italy, featuring international speakers and sponsors","breadcrumb":{"@id":"https:\/\/aiheroes.it\/2025\/speakers\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/aiheroes.it\/2025\/speakers\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/aiheroes.it\/2025\/speakers\/#primaryimage","url":"https:\/\/aiheroes.it\/2025\/wp-content\/uploads\/sites\/4\/live.png","contentUrl":"https:\/\/aiheroes.it\/2025\/wp-content\/uploads\/sites\/4\/live.png","width":220,"height":220},{"@type":"BreadcrumbList","@id":"https:\/\/aiheroes.it\/2025\/speakers\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/aiheroes.it\/2025\/"},{"@type":"ListItem","position":2,"name":"Speakers"}]},{"@type":"WebSite","@id":"https:\/\/aiheroes.it\/2025\/#website","url":"https:\/\/aiheroes.it\/2025\/","name":"AI Heroes 2025","description":"Artificial Intelligence conference","publisher":{"@id":"https:\/\/aiheroes.it\/2025\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/aiheroes.it\/2025\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/aiheroes.it\/2025\/#organization","name":"Synesthesia Events","url":"https:\/\/aiheroes.it\/2025\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/aiheroes.it\/2025\/#\/schema\/logo\/image\/","url":"https:\/\/aiheroes.it\/2025\/wp-content\/uploads\/sites\/4\/logo_AIHeroes.png","contentUrl":"https:\/\/aiheroes.it\/2025\/wp-content\/uploads\/sites\/4\/logo_AIHeroes.png","width":1080,"height":364,"caption":"Synesthesia Events"},"image":{"@id":"https:\/\/aiheroes.it\/2025\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/ai_heroes","https:\/\/www.linkedin.com\/showcase\/aiheroes-it\/"]}]}},"_links":{"self":[{"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/pages\/5292","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/comments?post=5292"}],"version-history":[{"count":122,"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/pages\/5292\/revisions"}],"predecessor-version":[{"id":5766,"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/pages\/5292\/revisions\/5766"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/media\/5229"}],"wp:attachment":[{"href":"https:\/\/aiheroes.it\/2025\/wp-json\/wp\/v2\/media?parent=5292"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}