Prophecy has launched Prophecy DataGPT, which lets business data analysts carry out complete data work inside ChatGPT, Claude and Microsoft Copilot, starting with messy source files and ending with finished reports. Each result arrives with a visual data workflow the analyst can inspect and validate, and once the work is approved, it ships as repeatable code on the data platform the organization already owns.
An analyst describes the outcome they need, and DataGPT assembles the full workflow in the conversation, covering onboarding, preparation, analysis and output. Business data teams review and approve each step through the visual workflow behind every answer. A knowledge graph links business context to data workflows, so teams can apply their definitions and business rules consistently across projects. Approved workflows become data products that run on a schedule as governed code on the organization’s cloud data platform.
Today, when analysts upload spreadsheets into an AI app like ChatGPT or Claude to reconcile a quarter of transactions, the AI quietly writes and runs a script to produce the answer. The analysts can’t read that code, so they have no way to check the result or stand behind it. The workflow also disappears when the chat session closes. Nothing remains of the path from raw inputs to finished output, and the domain knowledge the analyst contributed along the way, such as revenue definitions and approved exceptions, is gone with it. The risk grows as more AI-generated data moves through the business. Gartner predicts that by 2028, “50% of organizations will adopt a zero-trust data governance as unverified AI-generated data grows.”
“Enterprise AI is moving from answering questions to doing repeatable work. Generating an answer has gotten simpler. The challenge now is making the underlying data verifiable, governed, and reusable. Companies that can close the gap between business intent and execution will improve decision velocity,” said Michael Ni, VP & Principal Analyst at Constellation Research.
“Coders got AI that changed the way they work, collaborating with them on code all the way from development to production, unlocking tremendous productivity. Business data analysts got question answering, and nothing else changed,” said Raj Bains, founder and CEO of Prophecy.
“We are closing that gap,” continued Bains. “Business analysts now get what coders got – the visual workflow behind every result, in a form they can verify and change, built on governed knowledge. The work worth keeping moves to production on their data platform.”
AI assistants handle questions about data that has already been prepared, but enterprise data teams rarely get to start there. Most of their time goes into getting data ready by onboarding files, reconciling systems that disagree, matching records that share no common key, and cleaning and transforming the results. From there they deliver reports and filings in exact formats, where every number has to be correct and verified.
DataGPT is designed for line-of-business analysts, including finance and operations teams, who work in spreadsheets and desktop tools. Within one conversation, an analyst can upload a messy Excel file, check it against an audit list and data in SharePoint and Snowflake, apply a pricing rule for discounted product bundles, review the results and schedule the workflow to run again each month. DataGPT connects to files, SharePoint, data warehouses, and ERP and CRM systems, and every workflow is backed by open code in Git, so the logic stays transparent and auditable.
With DataGPT, the AI builds each workflow and the analyst verifies it visually, reviewing each step and its output on screen and approving the final version once any refinements are made. Approved workflows rerun exactly the same way every time, with no new AI generation and no added AI cost.
Pasting company spreadsheets into AI chat tools without IT’s knowledge or approval has become one of the most common forms of shadow AI among business analysts. With DataGPT, uploaded files pass through Prophecy to the organization’s own data platform instead of into an AI chat. Data platform leaders and IT can see every workflow and govern it on the platform they already run, without adding another silo.
Prophecy DataGPT is available today in all three chat apps and in the Prophecy app. Organizations can start with a free account, and administrators have centralized deployment options.
