NEWS, 16 SEP 2026, read 13 Nov 2026
Fivetran and dbt Labs announce dbt State, dbt v2 and a context layer for agents
Fivetran and dbt Labs issued a press release from dbt Summit 2026 in Las Vegas dated 16 Sep 2026. It announced general availability of dbt v2 and dbt State, and introduced Fivetran Context Layer, new dbt Wizard experiences, dbt Charts and an open lakehouse vision.
Per the release, Fivetran Context Layer is in private beta and builds on dbt's structured context while adding unstructured knowledge such as docs and Slack threads. It uses Agents Schema, an open source standard that places context in the warehouse, and teams reach it through MCP or other AI tools. The companies say every model, test and metric customers have defined already captures the context agents need. dbt State, per the release, checks warehouse metadata and model SQL to decide whether each run builds, skips, clones or defers a node.
For readiness, dbt's tests, contracts and exposures are the raw material of a label, and the release says the layer carries that material to agents. It does not describe a pass or fail readiness label, and the context layer is a private beta as of 13 Nov 2026. A team on dbt can already read test results in its own project, so a label rule built on them need not wait for the beta.
More readiness news
- Monte Carlo adds an Analytics API that reports data health through its MCP server4 Nov 2026
- Databricks makes data quality monitoring anomaly detection generally available29 Oct 2026
- Qlik introduces Semantic Models for data products and plans MCP tool support28 Oct 2026
- DataHub 1.8.0 nests data products and adds a Monte Carlo ingestion source22 Oct 2026
Sources
- www.getdbt.com/blog/fivetran-dbt-labs-announces-new-capabilities-to-make-enterprise-data-agent-ready-at-dbt-summit, read 13 Nov 2026
Last reviewed 13 Nov 2026.