dbt Labs Blog2026년 10월 26일

What Okta learned governing context for AI agents at scale

요약

Okta moved its AI agent context out of the Snowflake UI and into dbt, using a three-layer framework of agent metadata in model YAML, markdown context docs, and semantic views in dbt's semantic layer spec, all shipped through normal pull requests. The context syncs into Agents Schema, so Claude (over MCP) and Snowflake Cortex read the same governed rules, and an analytics engineer fixes a wrong answer by merging one change that every agent inherits.

Okta rebuilt how it governs context for AI agents, using dbt as the single source of truth.

원문 보기 →영어로 보기

What Okta learned governing context for AI agents at scale

관련 기사

How Data Culture measured its way from zero trust to a shippable AI analytics agent

How Verily Health monitors wastewater for 30-plus pathogens with a 5-person team and 1 dbt package

How Kramp cut analyst onboarding from days to minutes with a self-serve dbt Mesh factory

How customer pressure pushed dbt past a cautious platform team at Delivery Hero