AWS customers launch tens of billions of EC2 instances yearly, choosing from an expanding selection of compute, storage, memory, and networking options. This session reveals how innovations like the Nitro system and Graviton CPUs offload tasks to hardware, delivering improved performance and security. You'll discover how these technologies transform what was once impossible into reality for your workloads

This demonstration showcases how conversational AI can create tangible objects through an innovative AWS-powered workflow. Using Amazon Bedrock, Nova Pro, and SageMaker, the system transforms user conversations into personalized 3D-printed keychains. The live demonstration illustrates how businesses can combine generative AI and manufacturing to create unique, personalized customer experiences.

Agentic AI is everywhere, but do we always need an agent? In this fast-paced and interactive session, we’ll play a game of “Is It an Agent?” and try to figure out which problems really need agents… and which are just apps in disguise.

Agentic AI is everywhere, but do we always need an agent? In this fast-paced and interactive session, we’ll play a game of “Is It an Agent?” and try to figure out which problems really need agents… and which are just apps in disguise.

We kick off the evening in style with a warm welcome and lots of great insights from our very special guest AWS Chief Evangelist Jeff Barr on how AI is redefining the boundaries of software development and inspiring new possibilities in engineering.

We kick off the evening in style with a warm welcome and lots of great insights from our very special guest AWS Chief Evangelist Jeff Barr on how AI is redefining the boundaries of software development and inspiring new possibilities in engineering.

AI agents are a new class of software applications that use AI models to reason, plan, act, learn, and adapt in pursuit of user-defined goals with limited human oversight. Building AI agents that can reliably perform complex tasks has become increasingly accessible thanks to open source frameworks like Strands Agents. However, moving from a promising proof-of-concept to a production-ready agent that can scale to thousands of users presents significant challenges.

Through hands-on demos, we'll build a system from scratch and progressively deploy it to production using the comprehensive enterprise-grade services provided by AgentCore. You'll learn to implement key production capabilities, including secure session isolation, persistent memory, identity management, and real-time observability. The learnings can be applied to any framework and model, hosted on Amazon Bedrock or elsewhere.

nAIxt est la plateforme de développement et d'orchestration d'Agents IA d'ILLUIN Technology : un environnement unifié pour concevoir, déployer et surveiller des Agents IA, du POC à la production, nativement intégré à AWS. En 20min Aurèle Dalibot et Bastien Sivera aborderont les sujets suivants :

- Création d’un Agent IA en quelques minutes, du design à l’exécution

- Orchestration multi-agents : planifier, collaborer, se répartir les tâches

- Intégration native de nAIxt à votre environnement AWS pour créer des agents intelligents longue durée, en capitalisant sur vos données et services actuels en toute sécurité

- AWS Bedrock pour sélectionner / combiner les modèles d'IA adaptés aux cas d’usage

Pourquoi venir ?

Pour découvrir un outil de conception et d'orchestration d'IA Agentique qui permet d'automatiser vos processus métiers, d'accélérer votre time-to-market tout en garantissant la sécurité, la scalabilité, l'observabilité et le pilotage des systèmes agentiques.

Pour celles et ceux qui n'ont peu ou pas d'experience avec le cloud, ça peut paraître un peu effrayant de se lancer. Cette session va vous montrer les premières étapes à suivre vers son premier succès. A partir de là, on verra comment adopter au fur et à mesure des composants natifs du Cloud pour déveloper plus vite, adopter des bonnes pratiques, et optimiser les coûts

Dans les jeux de rôle sur table, le maître du jeu (MJ) occupe une place centrale : il tisse les histoires des joueurs, contrôle les personnages non joueurs (PNJ), crée des campagnes et décide si une action réussit ou échoue. Ce rôle demande une connaissance approfondie des mécaniques et des règles du jeu, alliée à un sens aigu de l’improvisation et de la créativité — un défi parfois écrasant. Dans cette présentation, nous verrons comment construire un maître du jeu multi-agents avec Strands afin d’assister les MJs dans leurs tâches

Romain Jourdan, Tiffany Souterre et Olivier Leplus, Developer Advocates chez AWS, partageront leur expertise et répondront à vos questions.

Offers strategies for preparing people, processes, and governance to adopt GenAI-enabled DevOps at scale.

Discusses how AI can enhance security, compliance, and reliability in AWS-based DevOps environments.

Showcases real-world use cases of Generative AI for developers and operations teams to improve productivity, reliability, and speed.

Explores how Amazon Q accelerates DevOps workflows by enabling AI-powered automation and improved orchestration within the DevOps lifecycle.

Outlines the technical foundations and key components required to implement smarter automation across DevOps pipelines.

When time is critical, finding the right clinical trial can mean the difference between hope and despair. In this session, Marshall Van Beurden, CTO at myTomorrows, shares how his team built a GenAI-powered platform on Amazon Bedrock that’s transforming this process—turning complex global trial data into life-changing matches with 98% accuracy and 90% faster than before

AI is redefining the future. Technology is changing faster than ever; people have new ways of interacting with technology, and organizations are adapting and adopting this change. However, Trusted AI can only be built on trusted data. We will dive deep into how AWS is helping customers build a trusted data foundation as they embark on their AI journey to build outcomes that are tailored to their business needs. HEMA will present their journey towards a strong Data Platform and Data Governance strategy on AWS, and the business outcomes they achieved.

Join Signify and AWS as we explore the journey of bringing natural language AI control to Philips Hue smart lighting. Follow their path through critical decisions around model selection, evaluation frameworks, and knowledge base architecture as they developed custom classifiers and orchestration flows to transform casual conversation into magical lighting experiences. See how AWS's evolving GenAI capabilities, from foundation model platform to enterprise-grade features, are helping organizations bring innovative AI solutions to production with confidence

Discover how Nationale-Nederlanden revolutionized its database infrastructure in this compelling case study. Join Matheus as he unveils the strategic journey from legacy Oracle and SQL Server on-premises systems to Amazon Aurora PostgreSQL Serverless v2. Get practical insights into architectural decisions, migration strategies, and key lessons learned from one of Europe's largest financial institutions.

Generative AI has incredible potential, but turning that potential into real-world impact requires more than just a proof of concept. Join Matheus Guimaraes for a journey into what it takes to bring generative AI into production — from adoption and development to testing, deployment, and observability. Along the way, you’ll see how new patterns like agentic AI, open-source frameworks like Strands, and AWS services like AgentCore are reshaping the way we build with AI.

Organisations struggle with justifying investment this year on AI strategy when the payback and impact to the workforce is so dynamic, that it causes frustration with users. Hear from Jason Yung on how he has observed the lessons learnt, and the areas to consider to ensure you have the right preparation discussions to align Mindset and People to the strategy, rather than building a strategy that no one truly believes in

PDFs are packed with text, tables, and images, but extracting insights from them isn’t easy. Traditional methods involve multiple components like OCR and task-specific models—making them complex and hard to scale. Vision-Language Models like ColPali simplify this by representing all modalities in a unified format.In this session, you’ll see how ColPali can be combined with OpenSearch to enable conversational search over rich PDF content. We’ll also showcase a live demo to bring this concept to life.