GenAI systems are evolving beyond basic information retrieval and question answering, becoming sophisticated agents capable of managing multi-turn dialogues and executing complex, multi-step tasks autonomously. However, reliably evaluating and systematically improving their performance remains challenging. In this session, we'll explore methods for assessing the behavior of LLM-driven agentic systems, highlighting techniques and showcasing actionable insights to identify performance bottlenecks and to creating better-aligned, more reliable agentic AI systems.

In this session, we will explore DeepSeek’s transformative impact on AI development, highlighting its potential to enhance enterprise innovation at a price/performance that is unprecedented. Data, analytics & AI leaders can bring their questions on how they can capitalize on new training and inferencing paradigms in AI, the future of AI model development and the impact of reasoning models on a more autonomous future in AI.

Organisations adopting a Data Mesh framework often face challenges in ensuring regulatory compliance, transforming data assets into scalable products, and maintaining governance. Explore how NatWest addresses these complexities by integrating knowledge graphs with GenAI and LLMs to enhance data discovery, enforce governance policies, and accelerate product development. Learn how this approach strengthens regulatory data qualifications, automates metadata management, and delivers faster, more reliable insights— to build and scale AI-driven data products yielding a potential 10x efficiency gain.

Despite the popularity of retrieval-augmented generation, organizations are struggling to optimize large language model applications based on RAG. Attend this session to get suggestions and recommendations on improving your RAG solution, LLMOps for RAG systems and scaling considerations.

This session is crucial for organizations aiming to maximize the utility of large language models by integrating internal data. Gain actionable insights and practical solutions to improve model performance and business outcomes. Ideal for technology leaders, data scientists and business strategists looking to harness the full power of LLMs.

AI's potential depends on quality data. Many struggle with AI due to data governance or slow processes, especially with unstructured data. Join peers in discussing strategies for improving and governance to maximise AI potential, managing structured and unstructured data, connecting LLMs with enterprise data and data security best practices.

As we enter an increasingly AI-driven world, it is becoming increasingly clear that leveraging the power of LLMs presents considerable challenges. Hallucinations, trust issues, and governance risks cause considerable concerns. This session will demonstrate how comprehensive and relevant metadata forms the foundation of data understanding and governance. You'll see how Ab Initio’s platform enables the automation of trusted, well-documented, and end-to-end governed data products, ensuring AI models operate with greater reliability and confidence.