"Data readiness" is a Myth: Reliable AI with an Agentic Semantic Layer
summary
Claims a self-improving, AI‑maintained semantic layer that converts messy enterprise data into reproducible queries by generating promql plans (a deterministic DSL) and executing them outside the LLM, avoiding RAG hallucinations. Live demos show the system learning from corrections, mapping 47 business terms, discovering 12 calculation variants, and reaching 100% accuracy on hard questions for a Fortune 500 food chain and a fintech. PromQL connects Snowflake/ZenDesk/Stripe and issues actions while versioning semantic builds.
AI-written summary · about
chapters (6)
related talks
47mThomas in't Veld | AI Track | Compass AI & Data Summit 2025
47mSemantic Layer: make your data speak with AI without hallucinations
11m68% of enterprise AI fails here—here's how to fix it
19mSession: Game Data For All: How AI Is Democratizing Game Analytics
38mRedefining Test Data Strategy in the Gen AI Era
23mTrusted Agentic AI:Architecting Systems with Reliable Data at Scale
19mHow to use generative AI to deliver self-service data products
32mIntelligent Data Platform : Powered by Semantic Layer, MCP & Agents