Describe your data pipeline. Get a Tableau Prep file.
cwprep generates .tfl and .tflx files from natural language. No drag-and-drop in the Tableau Prep GUI required — describe your data cleaning steps, and get a working flow you can open and run directly.
Core Capabilities
Files that work, every time
cwprep builds Tableau Prep flows using the exact same file format Tableau Prep uses internally. Files open correctly every time — there's no translation layer, no compatibility risk.
Translates 30+ Tableau Prep functions: DATEPART, ZN, IFNULL, and others become portable SQL that works across databases.
Safe to use in pipelines: Automatic backups prevent file corruption if a job fails mid-run.
Describe the result, not the steps
Describe the end state of your data — cwprep figures out the node order and connections automatically.
Runs in your build pipeline
Plug cwprep into your build scripts. Generate new data flows on every deploy, or batch-build pipelines for multiple clients.
Capability Matrix
| Feature | cwprep (Headless) | Tableau Prep AI | Advantages |
|---|---|---|---|
| Transparency | Full SQL output at every step | GUI blackbox — no SQL view | Share the SQL with your DBA or compliance team. No guessing what Tableau Prep did under the hood. |
| Runs without GUI | Yes (code and prompt driven) | No (requires visual interface) | Build dozens of pipelines in parallel from a script. No waiting for GUI renders. |
| Your choice of AI | Any MCP-compatible model (Claude, ChatGPT, DeepSeek) | Official cloud only | Use your company's private model if needed. No data leaves your network unless you choose it. |
Datacooper
Full SQL output at every step
Official AI
GUI blackbox — no SQL view
Share the SQL with your DBA or compliance team. No guessing what Tableau Prep did under the hood.
Datacooper
Yes (code and prompt driven)
Official AI
No (requires visual interface)
Build dozens of pipelines in parallel from a script. No waiting for GUI renders.
Datacooper
Any MCP-compatible model (Claude, ChatGPT, DeepSeek)
Official AI
Official cloud only
Use your company's private model if needed. No data leaves your network unless you choose it.
Product Roadmap
Phase 1: Foundation
Core node generation & full ANSI SQL translation.
Phase 2: Collaboration
Launch MCP shared server mode for team templating.
Phase 3: Governance
Integrate data quality gateways to stop skewed processes.
Pricing Options
- - Core TFL Builder Engine
- - Unlimited MCP Generation
- - Community Github Support
Frequently Asked Questions
Q: Is cwprep bound to a specific LLM?
A: No. cwprep is model-agnostic and supports Claude, ChatGPT, Gemini, and DeepSeek, as long as they support standard reasoning.
Q: Can the generated .tfl files be opened directly in Tableau Prep?
A: Yes. cwprep generates official .tfl and .tflx files that can be opened and run natively without plugins.
Q: Does it support complex row/column transformations (Pivot)?
A: Absolutely. cwprep is specifically optimized for Pivot and Unpivot node generation.
Quick Start
View Comprehensive Docs# 1) Installation
pip install cwprep
# 2) MCP Server Config Example
{
"mcpServers": {
"cwprep": {
"command": "uvx",
"args": ["--from", "cwprep[mcp]", "cwprep-mcp"]
}
}
}
# 3) Prompt Example
"Connect to intranet SQL Server (SSPI) to build a multi-database cleaning flow"
"Remove invalid columns, then execute Unpivot on month data"
"Finally output ANSI SQL with standard comments for audit review"