What’s Next in AI for Data and Data Management
summary
Claims that agents can take a topic description and build, evaluate and iterate a data stack are demonstrated with a demo pipeline that generates schema + questions + SQL, probes tables and measures table/column coverage and query complexity, then loops on metrics. Tools shown include RAG pipelines, LLMs and model families (small/medium enterprise models), plus document tools; accuracy sits in the low 20s–50s and cost per inference is falling.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 3:56Generative AI breakthroughs
- 9:57Evolving data landscape
- 16:19AI in data stacks
- 21:38AI-driven data management
- 27:13Autonomous data systems
- 32:32Demo: autonomous data product
- 38:30AI in data management future
- 41:43Q&A
related talks
47mThomas in't Veld | AI Track | Compass AI & Data Summit 2025
19mDatabricks
46mFullstack AI: The Building Blocks for Production Ready AI-Powered Software
21mHarnessing Technological Innovation & Accelerating Uptake
47mHow to Build Enterprise-Grade AI Agents Using Robust Evaluation
41mGenerative AI: bliss or miss?
38mRedefining Test Data Strategy in the Gen AI Era
01h 29mBuild Your Own Data Science AI Agents