Agentic AI

Agentic AI

The stage dedicated to Agentic AI and Agentic Experience Architectures, focusing on context-aware, adaptive intelligent systems that go beyond single-task automation.
Here you’ll explore examples and concepts on structuring autonomous AI flows for complex, personalized user experiences.

Room Hosting

Emanuele Arosio
Emanuele Arosio
CEO & Founder
DataRank
Sbarzaglia
William Sbarzaglia
Data Analyst & AI Consultant, Trainer, Speaker
Freelance
24 JUNE
25 JUNE
26 JUNE
I Patagarri - Live Concert I Patagarri - Live Concert
Valerio Lundini & I Vazzanikki - Live Concert Valerio Lundini & I Vazzanikki - Live Concert
Dardust - Live Concert Dardust - Live Concert
Ditonellapiaga - Live Concert Ditonellapiaga - Live Concert
N.A.I.P. - Live Concert N.A.I.P. - Live Concert
Opening Ceremony Opening Ceremony
24 june 11:50 - 12:20
30 min
24 june 12:40 - 13:10
30 min
In the era of autonomous AI agents, relying solely on Large Language Models (LLMs) can become inefficient. LLMs require costly infrastructure, consume significant amounts of energy, and are not well suited for edge devices. In addition, sending sensitive data to the cloud introduces latency, bandwidth costs, and privacy risks. This talk introduces Small Language Models (SLMs): models with millions—rather than billions—of parameters, designed for specialized tasks. These models consume less energy, provide faster inference, and can run directly on edge or embedded devices. Thanks to techniques such as quantization, pruning, and efficient fine-tuning, SLMs make it possible to move intelligence from the cloud to the edge, reducing latency while protecting local data. I will present use cases where SLMs are integrated into distributed architectures, from collaborative robots to IoT devices and federated systems designed for privacy preservation. I will also compare costs and performance with LLM-based approaches, illustrate optimization techniques, and introduce a method for migrating agents from general-purpose LLMs to specialized SLMs, following insights from recent NVIDIA studies. The goal of this talk is to demonstrate that micro language models are not only powerful enough for most agentic AI functions, but also represent a more sustainable and cost-effective alternative to general-purpose models, enabling a more democratic and widely accessible AI ecosystem.
24 june 14:30 - 15:00
30 min
24 june 15:20 - 15:50
30 min
As enterprises rush to deploy AI agents in customer-facing operations, most rely on one-time audits and manual testing. This approach offers limited coverage, surfaces problems only after the damage is done, and typically focuses on safety while ignoring accuracy, user experience, and operational efficiency. This session presents a practical framework for continuous AI monitoring and evaluation, drawn from deploying automated testing infrastructure across major European enterprises. Attendees will learn why point-in-time testing isn’t enough, how to implement live monitoring that catches failures before they become widespread, and what the EU AI Act actually requires in terms of ongoing oversight versus pre-deployment testing.
24 june 16:10 - 16:40
30 min
Agentic Experience Architectures (AEA) shift AI from task-based automation to journey-structured, context-aware, adaptive intelligence. Agents are organized by user journeys, splitting into: Journey agents that guide intent and decisions, Utility agents that provide memory, retrieval, reasoning, and governance. AEA introduces a layered orchestration model — planner → orchestrators → routers → agents — enabling traceability, safety, and efficient multi-agent collaboration. It fits best where reasoning and user experience must co-evolve (copilots, analytics, Vertical Saas, healthcare, creative tools, enterprise platforms). Security becomes zero-trust, policy-bound, and identity-based across all stages. AEA uses shared state and intent schemas to synchronize reasoning and UX, allowing adaptive, explainable interfaces. With reusable templates, observability, and continuous learning loops, AEA significantly improves:
latency, containment, trust, explainability, cost, and multi-agent yield.
24 june 17:00 - 17:20
20 min
The current landscape of AI technologies often feels like a Swiss Army knife: incredibly powerful, but business leaders are left guessing which tool to use for which problem. Furthermore, early enterprise attempts to deploy AI often rely on fragile, monolithic instructions that lead to unpredictable results, hallucinations, and high costs. This actionable session cuts through the hype to provide a practical, executive-level framework for building reliable AI solutions.First, we establish clear, strategic rules of thumb by walking through relatable enterprise scenarios, from field operations to executive data dashboards. We will demystify core AI architectures by focusing purely on their business utility: when to use AI for secure data retrieval, when to integrate it safely as hands within your existing enterprise systems, and when to deploy autonomous teams of agents to handle complex, multi-step workflows. Next, we introduce a paradigm shift in AI deployment: Agentic Skills. Instead of building unpredictable AI from scratch, attendees will learn how to implement modular, plug-and-play capabilities. These act as strict rulebooks and quality-assurance checkpoints, reducing errors and operational costs. Business leaders will leave this session equipped with the strategic clarity needed to stop experimenting with fragile AI and start deploying scalable, cost-effective solutions that drive tangible enterprise value without getting lost in the technical acronyms.
26 june 11:50 - 12:20
30 min
Supply chain teams spend countless hours on weekly reporting, transfer planning, and answering repetitive questions — high-frequency, low-value work that drains time and energy. We tackled these pain points with 3 purpose-built AI Agents: one auto-generates supply chain weekly reports, compressing hours of data collection and writing into minutes; another simulates transfer plans, rapidly producing multiple scenarios for decision-making; and a third serves as an always-on supply chain assistant, handling routine inquiries that once flooded inboxes. In this talk, I'll break down the design logic, implementation journey, and real-world results of each Agent — giving you a replicable playbook for bringing AI Agents into your own supply chain operations.
26 june 12:40 - 13:10
30 min
Participants will learn how to design AI roleplay agents as multi-agent systems. Rather than just building chatbots with a persona, they will understand how to structure scenario logic, define behavioral rules, and evaluate AI performance against learning objectives. The talk provides a reusable blueprint (covering architecture, alignment, and failure modes) that participants can directly apply to build, pilot, or evaluate AI-based simulations in their own training, education, or L&D programs. Participants will leave with a practical framework to design, test, and evaluate AI roleplay simulations in their own learning environments.
26 june 14:30 - 15:00
30 min
The enterprise applications services industry is facing its most significant business model disruption in decades. McKinsey now earns 20–25% of global fees from outcome-based pricing. They’ve deployed approximately 12,000 AI agents internally and shrunk typical project teams from 14+ consultants to 2–3 consultants plus AI agents. Meanwhile, 42% of companies abandoned most AI initiatives in 2025, and the average enterprise scrapped 46% of AI pilots before production. This speech delivers a practitioner’s playbook for system integrators building AI agent practices that actually make money. Drawing from a decade of enterprise software experience across multiple continents and ecosystems, the speaker introduces the Culture–Context–Code framework and a realistic 90-day sprint to first agent in production, followed by a 9-month transformation roadmap. Attendees will leave with a concrete operating model, specific pricing structures with real numbers, a step-by-step execution timeline, and a clear understanding of how to navigate the EU AI Act, DORA, and NIS2 regulatory landscape while building AI agent practices.
26 june 15:20 - 15:50
30 min
AI is evolving rapidly: from support technology to an agent capable of analyzing, designing, and acting within processes.In this scenario, the value of people is transforming: the importance of skills, the ability to interpret change, and leadership capable of giving direction, meaning, and responsibility to innovation are growing. Our role increasingly becomes one of orchestrating skills, data, technologies, and responsibilities, contributing to the governance of decisions augmented by artificial intelligence.The quality of this transformation also depends on the context in which AI operates: the culture it reflects, the values ​​it incorporates, the data it is trained on, the infrastructures and platforms it relies on, and the rules that govern it. This is why digital sovereignty is the ability to choose and build a safe, reliable AI that truly serves people, businesses, and the national system.Let's explore the new role of leadership in the age of agentic AI: guiding innovation, developing skills, preserving human judgment, and moving from theory to action. Because governing AI means understanding it, experimenting with it, and transforming it into sustainable solutions, with a conscious, courageous, and hands-on approach.
26 june 16:10 - 16:40
30 min
Why does AI agent design fail? More often than not, the issue is not the technology itself, but the design behind it. Service Design provides a framework for building agents that truly work: journey mapping, touchpoint design, and integration into existing workflows. MCP servers represent a key infrastructural layer, enabling agents to connect with external data and services while unlocking new experiences that transform software into intelligent collaborators and establish more advanced interaction models. From service blueprint to production, the approach is systemic, combining design and development through tools such as Figma, Claude Code, Replit, and vibe coding. A real-world case study on the design of an AI agent will also be presented.