Sumit Agarwal

RAG has emerged as a powerful approach for building advanced AI systems that combine the strengths of large language models with external knowledge sources. However, RAG solutions struggle with reliability and require a lot of experimentation. This session will address key questions to help determine the best design pattern and optimization for RAG implementations.

AI governance is no longer optional. This session will explore practical strategies for embedding AI governance directly into the design and development of AI architectures, ensuring that compliance, transparency and ethical standards are upheld from the ground up.

This session will provide a blueprint for the comprehensive data, analytics, and AI capabilities and services that leaders need to build to enable their organization's AI ambition. It will explore the implications of your AI ambition archetype on your buying, deployment, and organization strategies.

RAG has emerged as a powerful approach for building advanced AI systems that combine the strengths of large language models with external knowledge sources. However, RAG solutions struggle with reliability and require a lot of experimentation. This session will address key questions to help determine the best design pattern and optimization for RAG implementations.

AI agents can upend traditional AI use cases and unlock transformative potential, but the real danger isn’t overhyping their power — it’s overestimating your organization’s readiness. D&A leaders must see past the hype, sidestep common pitfalls, and build the foundation needed for true AI success.

GenAI solutions include several choices and trade-offs. A critical decision is: should you build custom AI solutions in-house or buy off-the-shelf products? This session brings together a debate on the trade-offs, risk and rewards of each approach. The session will be based on scenarios and use-cases to highlight key considerations such as cost, reliability , flexibility and speed for different decisions such as LLMs vs. SLMs, RAG vs. AI agents, packaged platform capability vs. bespoke custom solution, packaged vs. open-source.

RAG has emerged as a powerful approach for building advanced AI systems that combine the strengths of large language models with external knowledge sources. However, RAG solutions struggle with reliability and require a lot of experimentation. This session will address key questions to help determine the best design pattern and optimization for RAG implementations.

RAG has emerged as a powerful approach for building advanced AI systems that combine the strengths of large language models with external knowledge sources. However, RAG solutions struggle with reliability and require a lot of experimentation. This session will address key questions to help determine the best design pattern and optimization for RAG implementations.

GenAI solutions include several choices and trade-offs. A critical decision is: should you build custom AI solutions in-house or buy off-the-shelf products? This session brings together a debate on the trade-offs, risk and rewards of each approach. The session will be based on scenarios and use-cases to highlight key considerations such as cost, reliability , flexibility and speed for different decisions such as LLMs vs. SLMs, RAG vs. AI agents, packaged platform capability vs. bespoke custom solution, packaged vs. open-source.

AI governance is no longer optional. This session will explore practical strategies for embedding AI governance directly into the design and development of AI architectures, ensuring that compliance, transparency and ethical standards are upheld from the ground up.

Despite their trillions of tokens of training data, GPT4 and others models can’t answer a single question about us as unique individuals. The personal AI assistant we all want surely has to know us as individuals, right? Today’s AI assistants either give us generic information, or require significant input from us before providing useful personalized assistance. Isn’t there a better path?