Skip to main content
This page collects the questions the PrettyWhale team hears most often. Whether you are evaluating the platform, setting up your first pipeline, or troubleshooting a specific step, you should find a direct answer below. If something is still unclear, reach out at contact@prettywhale.ai.
PrettyWhale is an AI-powered platform that generates production-ready data pipelines from a sample data file. Upload a file, configure your pipeline settings, and PrettyWhale.ai produces ingestion code, unit tests, data quality checks, schema definition, and pipeline documentation. It eliminates the repetitive, error-prone manual work of writing ingestion code from scratch.
PrettyWhale.ai is really different from copilots. Those tools work inside your editor and answer the question you are typing. They are good at it but they need you as a guide. The unit they produce is a suggestion, and an engineer decides what to do with it.PrettyWhale.ai produces the unit above that one: a project you can run, with the tests that prove it runs and the documentation that lets someone else maintain it. Copilots suggest. Engineering AI delivers.
PrettyWhale.ai currently accepts JSON and CSV sample files. For the full list of supported formats, tips on structuring your sample file, and best practices for getting the best generation results, see Supported Formats.
After you import a sample file, PrettyWhale.ai runs an automatic field discovery pass. It inspects every field in your data: inferring data types, detecting nullability, identifying value patterns, and flagging potential quality issues such as inconsistent formats or out-of-range values. The results appear in the field analysis interface, where you can review each field and choose which fields to include in the generated pipeline before moving on to transformations.This discovery step is what allows PrettyWhale.ai to produce accurate schemas and targeted quality rules rather than generic boilerplate.
Every pipeline generation produces the same artifacts:
  1. Executable code
  2. Unit tests
  3. Output Schema
  4. Configurations files
  5. Pipeline documentation
All artifacts are generated together and are consistent with one another. You do not need to write or align them manually.
No. PrettyWhale.ai is not a general-purpose code assistant or conversational AI. It uses a proprietary Small Language Model (SLM) that has been fine-tuned specifically for data engineering tasks. That specialization is what makes the generated code consistent, validated, and production-grade. You will not use it to write a web server or a React component for example.  It is purpose-built for ingestion pipelines, and that focus is intentional.
Discovery and Transformations stages typically complete within seconds after you upload your sample file and configure your pipeline settings.The exact complete duration depends on the size and complexity of your sample file, but for most standard inputs you will have all artifacts ready in minutes.
Yes. At the end of the generation cycle, the pipeline is executed on our infrastructure before it is packaged. It runs on the sample you provided and the tests are also executed. Thus, what lands in your repository has already been executed.That step is what separates our generated pipelines from a copilot’s suggestion. A suggestion is first judged on whether it looks right. Our pipelines are judged on whether they run, and we would rather find that out before you do.
You can reach the PrettyWhale.ai team at contact@prettywhale.ai or through the contact form at prettywhale.ai/contact.
No. Your sample is used to generate your project and nothing else. It does not become training material, for us or for anyone else.