Data2Story turns a CSV file into a verified interactive news article using seven AI agents
74% of readers preferred AI-generated news over human originals. Data2Story just proved it.
Why it matters
A multi-agent AI system (seven coordinated agents) is shipping real product capability: turning raw data into verified, interactive news articles with sourced claims. This is app-layer AI deployment at work—not a model benchmark, but a working tool that's already outperforming human journalists in reader preference, signaling where content automation is headed.
The key facts
13 to knowSeven AI agents orchestrated in newsroom-style workflow
Data Journalist Agent from Oxford and Stanford research
93% of statements include verifiable source links
74% reader preference over human original articles
Tied performance against long-form crafted reports
CSV-to-interactive-article end-to-end automation
Multi-modal output: graphics + web research + links
Seven AI agents work collaboratively in newsroom-style workflow
Data Journalist Agent converts CSV files into interactive articles with graphics
74% reader preference over human original in user study
Tied performance against long-form human reports
Agents developed by researchers from Oxford and Stanford
Web research and source integration included in output
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Seven AI agents work together like a newsroom. The "Data Journalist Agent" from Oxford and Stanford turns a CSV file into a finished interactive article with graphics, web research, and verifiable source links for 93 percent of all statements. In a reader study, 74 percent preferred the agent's…