Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.prophecy.ai/llms.txt

Use this file to discover all available pages before exploring further.

Prophecy helps analysts generate, refine, and operationalize data workflows with AI. Describe the workflow you want, generate pipelines with AI, refine them visually or in SQL, and run recurring workflows directly on your data platform. Generated workflows remain editable, reusable, and production-ready from the start. Getting started is easy. Just sign up, create a project, and build your first workflow.

Getting started

Sign up for the Free Edition

Create a free account and start building your first workflow

Quickstart

Build your first AI-generated pipeline in minutes

Build with Agent

Describe workflows in natural language and generate pipelines with AI

Review and refine

Review generated workflows

Review, validate, and refine AI-generated pipelines visually or in SQL

Concepts

Learn core concepts like pipelines, workflows, and parameters

Use parameters and reusable workflows

Build flexible workflows that adapt across teams, schedules, and runtime environments

Extend existing workflows

Share and reuse workflows

Share projects and reusable workflows across teams

Schedule and run workflows

Run recurring workflows on schedules or trigger them automatically

Import workflows

Import existing Alteryx workflows and extend them with AI

Why teams use Prophecy

Prophecy helps data teams move from ad-hoc analysis to reliable operational workflows faster with AI.

Built for analysts and data teams

Analysts

  • Build SQL pipelines and recurring workflows
  • Generate and modify transformations using natural language
  • Turn ad-hoc analysis into reusable operational workflows
Start here:

Engineers

  • Build Spark-native pipelines using visual or code-first workflows
  • Develop production workflows for ingestion, transformation, and orchestration
  • Deploy and monitor workflows running on your cloud data platform
Learn more: Data Engineering docs