6 min read
When dbt, Looker, and Metabase disagree on "revenue"
Reconciling contradictory metric definitions across dbt, Looker, and Metabase, and how ktx flags them instead of silently selecting one.
Read moreTopic hub
Explore semantic-layer strategy, governance controls, and where semantic layers fit in a broader AI analytics architecture.
Coverage
Start here
Why Every Growing Company Needs a Semantic Layer (And How AI Makes It Easy)Guides on semantic layers, metric definitions, and governance patterns for AI-ready analytics stacks.
Page 1 of 3
Reconciling contradictory metric definitions across dbt, Looker, and Metabase, and how ktx flags them instead of silently selecting one.
Read moreGenAI didn't create new data governance problems. It made the existing ones harder to ignore and added a new one: context. Why agentic analytics needs a governed context layer that sits alongside your whole stack, not just inside the warehouse.
Read moreStatistical foreign-key inference, validated against real data. How ktx builds the join graph agents rely on.
Read moreAnthropic published how its data team automated close to 100% of business analytics at 95%+ accuracy. The four-layer architecture they describe is the same one we had already open-sourced as ktx, an independent, Apache-2.0 context engine for data agents.
Read moreA context layer puts your warehouse schema, joins, metric definitions, and business knowledge in one reviewable place so data agents query governed context instead of guessing field names. A look at how it works, and at ktx, the open-source context layer.
Read moreFan and chasm traps, and how ktx compiles intent into safe SQL over a reviewed join graph.
Read morektx is the open-source, executable context layer for data agents. It ingests your data stack and internal docs and turns them into an executable semantic layer plus a wiki, so agents query ktx for correct SQL instead of guessing from raw schema.
Read moreA change-management workflow for AI analytics metric definitions, covering ownership, versioning, impact analysis, regression tests, release notes, and agent synchronization.
Read moreA practical migration playbook for data teams extending semantic-layer investments into a governed context layer for AI agents.
Read moreA data leader guide to why ARR, MRR, pipeline, churn, and revenue metrics break in AI self-serve analytics and how governed context fixes the problem.
Read moreA reference architecture for AI analytics covering warehouses, semantic layers, context layers, agent interfaces, access controls, and evaluation loops for production-grade deployments.
Read moreA practical guide to metric governance for data leaders, covering canonical definitions, ownership, semantic layers, change control, and how context layers extend metric governance to AI analytics.
Read more