BI and data governance · Available
dbt platform for Claude, ChatGPT and Copilot
Whether last night's jobs passed, which models are stale, which tests failed, what a Semantic Layer metric returns for a period: these are the questions people bring to the dbt platform, formerly dbt Cloud. mcpbizapps lets them ask in Claude, ChatGPT or Copilot. Roles decide which projects and environments each person reaches, and job changes need the owner's approval. Setup runs as a guided pilot with your analytics engineers.
- Status
- Available
- Setup
- Guided pilot with your team
- AI assistants
- Claude, ChatGPT, Copilot Studio
- Access
- By role, view only or with approvals
Ask in a sentence
What can your team ask dbt platform?
Questions from analytics engineer, data analyst, head of data and others, answered from live dbt platform data and only for the people allowed to see them.
Records it works with
- Models
- Sources
- Tests
- Jobs
- Runs
- Environments
- Semantic Layer metrics
- Exposures
- Analytics engineer
“Which models failed in the production job last night, and what was the first error?”
- Data analyst
“Using the Semantic Layer, what was revenue by plan for each month this year?”
- Head of data
“How many runs of the daily job failed this month, compared with last month?”
- Finance analyst
“Is the fct_invoices model fresh enough to use for this morning's close review?”
- Data steward
“Which models in the marketing folder have no tests or no description?”
- Analytics lead
“Which sources missed their freshness threshold this week?”
Changes, governed
What the assistant can prepare in dbt platform
The assistant never saves on its own. It prepares the change, the person checks the preview and confirms, and anything above your limits waits for an approver.
- 1 Prepare The assistant drafts the change from the request.
- 2 Preview and confirm The person sees exactly what will change.
- 3 Approve Above your limits, a second person decides.
- 4 Saved and logged Written to dbt platform under a named person.
-
Pause the schedule of a job while a source is down
The project owner confirms; pausing jobs that feed finance models needs the finance data lead.
-
Change the time a scheduled job runs
Development jobs can move on the person's word; production jobs need the analytics lead.
-
Open a ticket for a failing test with the run details
A ticket touches no data, so the person confirming is enough before it reaches the model owner.
Example rules. During the pilot you set the limits, the approvers and which roles may prepare each change.
Why it needs care
Governance built for dbt platform
dbt platform jobs decide when production models rebuild, and a paused or moved job can leave finance or sales numbers stale. Assistants read run history, tests and metrics by role. Any schedule change comes with the list of models it touches, so the owner can judge the effect before approving. Actions are recorded against a person.
-
Sign-in by work email
Only people you invite, with a one-time code. No shared logins.
-
Roles per tool
Each role reaches only the dbt platform records it needs.
-
View only, if you prefer
Admins can keep a connection to lookups with one switch.
-
A preview first
Every change is shown in full before anything is saved.
-
Approval rules
Above your limits, a second person approves the change.
-
One audit log
Every request tied to a named person, ready for review.
Setup
How dbt platform gets connected
We connect dbt platform for your team in a guided pilot, on the same gateway every app uses. No code on your side.
- 01
Agree the questions
We list the dbt platform questions and changes your team needs, and who may use each.
- 02
Connect with your admin
Your dbt platform administrator creates a dedicated integration user with only that access.
- 03
Test with your people
A small group tries it in Claude, ChatGPT or Copilot while we tune the tools.
- 04
Roll out with rules
Roles, approval limits and the audit log are in place before everyone joins.
Then people use it from the assistant they already have
dbt platform questions
Can ChatGPT query the dbt Semantic Layer?
Yes. The assistant asks for a metric by name with the dimensions and time grain you want, and dbt builds the SQL from your metric definitions. Answers match what your dashboards show, because both use the same metric.
Can an assistant run dbt models?
No. It does not run models or write to your warehouse. It reports on jobs and runs, explains failures from the logs, and prepares schedule changes or pauses for the job owner to confirm.
Does it work with dbt Core?
This connection is for the dbt platform, formerly dbt Cloud, which keeps job history, environments and the Semantic Layer in one place. For dbt Core projects, mcpbizapps can still answer questions from the warehouse models those projects build.
Does mcpbizapps keep a copy of our dbt platform data?
No. When someone asks a question, mcpbizapps reads the answer live from dbt platform through a dedicated integration user and returns it without storing it. The audit log records who asked, which tool ran and the result, with personal fields and free text removed.
dbt platform is a trademark of its owner. mcpbizapps is not affiliated with dbt Labs; the name describes the connection only.
Related
Often connected alongside dbt platform
Part of Data and analytics: Cloud warehouses, dashboards, governance and data pipelines.
Start
Bring dbt platform into your AI assistant
Tell us how your team uses dbt platform, and we will plan a guided pilot around your own questions.
- We agree the tools and approval rules with you
- Your admin creates the integration user; no code
- Business data is read live and not stored
Thank you
We received your request and will reply by email to find a time.
Last updated