Show Notes
In this episode of the Agile Data Podcast, host Shane Gibson sits down with Juan Sequeda, the principal scientist and head of the AI lab at data.world, and an expert in data integration and Semantic Web technologies. In this episode, the conversation explores the intricate world of knowledge graphs and business semantics. Juan explains how a knowledge graph operates as a flexible framework that makes real-world concepts and their relationships first-class citizens, extracting meaning out of isolated application code and linking it directly to the data. By focusing on business literacy and well-defined ontologies, knowledge graphs ensure that your architecture remains highly resilient and agile enough to handle the unknown use cases of tomorrow. The discussion also dives deep into the complexities of data integration, clarifying the crucial role of unique global identifiers. Juan breaks down how adopting web-based identifier standards, such as URIs, prevents ambiguity—like confusing the word “fire” as a termination, a weapon, or heat—and achieves seamless integration across multiple systems by definitively codifying real-world entities. Whether you are curious about how to build enterprise ontologies, how LLMs and knowledge graphs are combining to increase AI accuracy from 16% to 54%, or want to learn why your data catalog should be built on a graph architecture, this episode is packed with valuable insights for data professionals
You can get in touch with Juan via LinkedIn or over at https://www.juansequeda.com If you want want to read a summary generated with GenAI, head over to: https://agiledata.substack.com/i/202701645/google-notebooklm-briefing
If you want to download the transcript for the podcast, head over to: https://agiledata.substack.com/i/202701645/transcript
Listen to more podcasts on applying Agile Data patterns over at https://podcast.agiledata.io/ Read more on the Agile Data Way of Working over at https://AgileDataGuides.com/
If you just want to talk about making magic happen with agile and data you can connect with Shane @shagility on LinkedIn.
Subscribe: Apple Podcast | Spotify | Google Podcast | Amazon Audible | TuneIn | iHeartRadio | PlayerFM | Listen Notes | Podchaser | Deezer | Podcast Addict | Buy the Green Book now!
Simply Magical Data Ways of Working
More from Agile Data N’ Info
In this episode Shane Gibson sits down with data modeling veteran’s John Giles and Remco Broekmans The conversation explores the premise of democratising data modeling through AI, centered around a paper published by John regarding where AI can and cannot add real value. The group highlights the critical importance of conceptual and context data modeling, stressing that business terms and definitions must be established upfront before looking at physical source tables. They strongly critique the anti-pattern of placing humans “at the end of the line” merely to rubber-stamp automated outputs, arguing instead for an “AI-in-the-loop” approach where technology serves strictly as an assistant under human direction. The discussion also dives deep into complex real-world scenarios where automated tools fail—specifically when physical data or source systems do not yet exist. John shares extreme edge cases, such as establishing a brand-new government department from scratch based on a vague Act of Parliament, unifying over 70 distinct healthcare organisations into a single model, and modeling evolving visions like the Australian wool industry. Remco breaks down his multi-agent ELM framework, explaining how introducing deliberate manual friction points between LLM tasks keeps human modelers in control and why model-storming workshops, human trust, and organisational culture are far more vital than push-button automation. Whether you are curious about conceptual modeling techniques, how to effectively integrate “AI in the loop” while avoiding push-button modeling pitfalls, or strategies for aligning business definitions across complex organisations, this episode is packed with valuable insights for data professionals.
Raw and unedited Top 3 things:
Raw and unedited Top 3 things:
Raw and unedited Top 3 things:
Raw and unedited