Nested Tableau containers can consume a surprising amount of dashboard-building time. In this experiment, I asked an AI to infer a layout from a screenshot, save layout JSON and use cwtwb to generate a workbook.
The output deliberately used text placeholders. I explicitly allowed mocked calculations because this test was about layout construction.
The prompt's important boundary
Generate the layout JSON and save it locally, then use this JSON
to generate the final dashboard. I don't need you to perfectly
replicate the calculations; you can just mock up a few.
This is an excerpt from the original prompt, rather than a runnable SDK example.
Why the intermediate JSON helps
The workflow has three inspectable stages:
Reference screenshot -> layout JSON -> Tableau workbook (.twb)
A screenshot communicates arrangement. The layout description makes horizontal and vertical nesting explicit. The workbook turns that description into an artifact that can be opened and edited in Tableau.
The generated skeleton looked unfinished because its job was to expose structure, not to impersonate a verified production dashboard. The container hierarchy was the focus of the original review.
What still needs to happen
This demonstration does not establish pixel-perfect replication or calculation correctness. Real data bindings, calculations, styles and interactions need their own implementation and checks.
That distinction is central to cwtwb's development: build from public SDK operations, then verify the artifact against a concrete case. Datacooper's planned paid MCP should help carry that workflow further toward finished BI work, with reviewable intermediate results.
Originally shared in this LinkedIn post.
Explore cwtwb on GitHub, the case replication repository and Datacooper.
Top comments (0)