In this informal conversation, Roelant Dieben, AI MVP, engages Microsoft AI leaders on the future of AI and the role of community in shaping it. Discover how MVPs influence product direction through feedback loops, drive innovation with agentic AI, and help Microsoft build tools that reflect real-world needs. This session offers a candid look at how collaboration fuels the evolution of Microsoft Foundry.
talk-data.com
Speaker
Pablo Castro
4
talks
Pablo is a Corporate Vice President and Distinguished Engineer at Microsoft. He currently leads the AI Knowledge team, part of the CoreAI division, where he focuses on building state-of-the-art knowledge understanding and retrieval systems for AI applications and agents, including products such as Azure AI Search and Azure Content Understanding. Pablo’s interests include information retrieval, machine learning, distributed systems, and database systems.
Bio from: Microsoft Ignite 2023
Filter by Event / Source
Talks & appearances
4 activities · Newest first
Agents need context. How should we connect data to our agents for optimal context? In this session we will introduce Foundry IQ, the knowledge layer for agents, and the latest developments from Azure AI Search and Microsoft Foundry. Learn about multi-source RAG orchestration, retrieval steering, dynamic security controls and agentic RAG.
Azure AI Search is a full-featured knowledge retrieval system, built to power enterprise-ready RAG applications. Join this session to learn about our latest announcements and our continuous momentum for delivering trend-setting search, superior retrieval quality and enabling RAG at scale.
𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀: * Pablo Castro
𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻: This is one of many sessions from the Microsoft Ignite 2024 event. View even more sessions on-demand and learn about Microsoft Ignite at https://ignite.microsoft.com
BRK105 | English (US) | AI
MSIgnite
Generative AI apps are powered by a combination of reasoning and knowledge. In this in-depth session we’ll dive into knowledge retrieval, the role of vector search, how hybrid search and reranking models improve relevance, and how recent improvements make it easier to prepare and ingest data into knowledge bases. We’ll ground concepts with live code and data from our extensive evaluations on retrieval quality.
To learn more, please check out these resources: * https://aka.ms/Ignite23CollectionsBRK206H * https://info.microsoft.com/ww-landing-contact-me-for-events-m365-in-person-events.html?LCID=en-us&ls=407628-contactme-formfill * https://aka.ms/azure-ignite2023-dataaiblog
𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀: * Pablo Castro * Farzad Sunavala * Liam Cavanagh * Ed Donahue * Gia Mondragon * Allison Sparrow
𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻: This video is one of many sessions delivered for the Microsoft Ignite 2023 event. View sessions on-demand and learn more about Microsoft Ignite at https://ignite.microsoft.com
BRK206H | English (US) | AI & Apps