A dashboard generated by AI should leave you with a workbook you can keep working on. That was the question behind this early cwtwb experiment: could an agent assemble a Tableau dashboard without manually dragging sheets onto the canvas?
The screenshot shows the resulting workbook alongside the prompt. It includes sales by sub-category, sales by category, a monthly profit trend and a regional sales breakdown. The useful output is the Tableau .twb file, rather than an image of a dashboard.
How the workflow works
- Describe the charts and dashboard you need.
- The agent calls the MCP tools to configure workbook elements.
- The implementation writes the workbook structure, including worksheets and layout containers.
- Open the output in Tableau and review the result.
A TWB stores workbook definitions as XML. cwtwb provides a Python SDK so callers can work with higher-level operations instead of assembling that XML manually. MCP gives an agent a way to call those operations.
What this demonstration does and does not prove
This is a retrospective of an early prototype. The screenshot demonstrates workbook authoring; it does not prove every business calculation or interaction is correct. A production workflow also needs input checks, calculation validation, rendered output and tests of relevant parameter or filter states.
Today, the open-source SDK and the Workout Wednesday replication repository help make that review process concrete: a build script, locked input data, a workbook and recorded checks.
My planned paid MCP builds on that direction: help complete real BI tasks with clearer inputs, repeatable builds and evidence of the result. It remains a product plan, not a claim that every BI task is already automated.
Originally shared in this LinkedIn post.
Explore cwtwb on GitHub, the case replication repository and Datacooper.
Top comments (0)