dbt integration: AI agents for your data models
dbt is a SQL-based data transformation tool used by data teams to model, test and document tables in warehouses such as BigQuery, Snowflake and Databricks. The agent uses the dbt Cloud API, or the dbt MCP server, to read jobs, test results, models and project documentation.
What AI agents do with dbt
Job failed before the dashboard opened
When a dbt job fails overnight, the agent identifies the model and test that broke and tells the data team the likely cause.
Quality tests with context
When a uniqueness or accepted-values test fails, the agent shows which dashboards and teams depend on that model.
Metric questions answered
Anyone who asks how net revenue is calculated gets the definition from the dbt documentation, with the source model.
Model changes announced
When an important model changes, the agent notifies the owners of the affected reports.
Connect dbt once. The agents use it within your rules.
- Through the APIConnected through the app’s API: iTeam learns the endpoints from the documentation and the scope is confirmed in the diagnosis.
- Each agent gets the right accessYou decide what each agent can read or do in dbt, by area and by person.
- Human approval where it mattersSensitive actions wait until someone with the authority approves them.
- A trail and a cost for every actionWho asked, what the agent did in dbt and what it cost, all on record.
Ready-made AI teams for this work
Management reporting team
Revenue, margin, pipeline and cash in one report, built from your systems, with a short note on what changed and why.
Data analysis team
Ask which customers stopped buying or which region lost margin. The team writes the SQL, runs it and explains the result.
IT service desk team
Password resets, access requests and how-to questions handled in chat, with Jira updated and approvals in place.
Often used together with dbt
Questions about dbt and AI agents
Does iTeam integrate with dbt?
Yes. iTeam connects through the dbt Cloud API or the dbt MCP server, set up with your data team.
Can the agent change models in production?
Not by default. It reads and explains; code changes go through a pull request with human review and are recorded in the audit trail.
Does it work with dbt Core?
Yes, by reading project artifacts and run logs. The format is agreed in the diagnosis.
