AI Developer

Chairpersons welcome and opening remarks

What’s real vs. hype: Where GenAI is already delivering value in dev workflows, and where it still falls short.

• Velocity vs. quality: Does GenAI speed up coding without introducing new risks?
• Integration into the toolchain: How devs are embedding GenAI into IDEs, CI/CD, testing, and code review
• Shaping engineering culture: How pair programming with AI is changing team collaboration and onboarding
• Risk and control: Versioning, reproducibility, hallucinations — what engineers need to watch for
• What’s next: Multi-agent dev environments, AI debugging, and the future of human-in-the-loop coding

Generative Experiences, Autonomous Agents, Fulfillment Intelligence, and Trusted Ecosystems for the Next Retail Era Commerce is entering an AI-native era, where intelligence is embedded across the entire commerce lifecycle – from seller onboarding to post-purchase engagement. This talk presents a full-stack blueprint for how generative AI, autonomous agents, fulfillment intelligence, and trust infrastructure are transforming modern e-commerce platforms. This session offers both technical depth and strategic insights for building scalable, intelligent commerce ecosystems that serve sellers, empower buyers, and sustain platform trust.

As AI agents move into production, grounding enterprise data is no longer enough. This session explores how a Fortune 500 insurer engineered an identity-aware memory layer using entity resolution to improve agent reliability and decision-making. Covering architecture, system integration, engineering trade-offs and deployment lessons, attendees will gain practical patterns for building more accurate, production-ready AI agents.

When millions of users complete transactions globally, any friction during checkout leads to lost conversions and drop-offs. Selecting the right payment method is an optimization problem driven by geography, device, order context, and user intent. In this session, we will explore how Uber leverages machine learning to personalize payment flows, especially for new users. We’ll cover point-wise ranking for payment onboarding, intelligent pre-selection to streamline the first time user experience, key lessons learned when models directly influence user behavior, and how ML navigates real-world trade-offs.

Getting an LLM to answer a question is easy. Building an AI application that remains reliable, observable and maintainable at scale is not. This session explores the emerging engineering discipline around production AI, including orchestration, context engineering, evaluation, memory, observability and governance and why these systems are becoming more like distributed software than traditional machine learning.

“Why Your RAG Sucks and How to Fix It” dives into the common pitfalls of Retrieval-Augmented Generation (RAG) implementations, from poor retrieval quality to misaligned embeddings and hallucinations. This session will break down why many RAG systems fail to deliver accurate, relevant, and trustworthy outputs—and provide practical strategies, tools, and best practices to fix them. Attendees will leave with actionable insights to optimize RAG pipelines, improve retrieval accuracy, and build AI systems that actually get things right.

As AI applications evolve from conversational interfaces to intelligent systems capable of reasoning, planning, and taking action, development teams are rethinking how AI products are designed and deployed.

This panel brings together AI engineers, architects, and technology leaders to explore the emerging architectural patterns behind modern AI-native applications. From retrieval-augmented generation (RAG) and agentic workflows to context management, memory systems, orchestration frameworks, and evaluation pipelines, panellists will discuss the technologies and design decisions enabling more capable, reliable, and scalable AI experiences.

Join the discussion as experts share lessons from production deployments, highlight common pitfalls, and examine how application architectures are evolving to support the next generation of AI-powered products.

As AI systems move into production, ensuring ethical, transparent, and accountable deployment is more important than ever. This presentation explores practical strategies for embedding responsible AI principles into the development lifecycle, including bias detection, fairness auditing, explainability, and governance frameworks. Attendees will learn how to implement safeguards that balance innovation with accountability, enabling AI solutions that are trustworthy, compliant, and aligned with organizational values.

The faster path to production AI is an API key and a frontier model. GLS chose control instead: a customer-service system built on self-hosted, open-source small language models, live across several countries in Europe, automating millions of customer interactions between GLS and the people receiving their parcels. This session is explores the engineering road, which started two years ago – building a multi-agent solution with SLMs from scratch, while meeting regulatory requirements. Bernat Coma Puig, AI Lead at GLS, will cover the architecture design, the challenges and how to solve them: from guardrails, scalability, response accuracy, and keeping costs predictable and under control at scale.