toVeriAI
Truth isn’t binary: a score that explains how far you can trust a news story.
A web platform that analyses news, links and screenshots with AI and returns the IMI, a 0–100 credibility score that shows what is wrong and where.
Disinformation is not always an obvious lie: often it is a figure with no source, an alarmist tone or a quote from experts nobody identifies. Labelling a story “true” or “false” falls short and often breeds more distrust.
toVeriAI analyses the text across seven content dimensions, plus two about the outlet when a link is analysed, and combines them into the IMI (Interpretive Metrics Index). It highlights problematic fragments in the text itself and ends with a summary that explains the result. The methodology builds on NewsGuard and is completed with IFCN and The Trust Project criteria.
toVeriAI is live at toveriai.com: five languages, free use without an account, accounts with history and statistics, and a Premium plan in beta. Alongside it, VeriAI is being trained: an in-house model that learns from every analysis.
- IMI score from 0 to 100: It starts at 100 and deducts for each alert according to its dimension’s weight. Above 70, high credibility; below 40, low.
- Highlighted fragments: Every alert is marked in the text itself, with its category, so you can see exactly where the problem is.
- Text, link or screenshot: With a link it also checks the outlet’s website to assess its transparency and authorship. Screenshots work for social media.
- Five languages: Spanish, Galician, Catalan, Basque and English, in both the interface and the analyses.
- Community and outlet tracking: A moderated public feed with per-dimension votes, an outlet ranking and alerts when the average reliability of an outlet you follow changes.
- VeriAI, an in-house model: A local model that re-runs every analysis in the background and learns from the differences with cloud providers.
- Galivelop-workflow: If it isn’t pushed, it doesn’t exist: the way we work with AI, packaged for any project.
- toVeriAI: Truth isn’t binary: a score that explains how far you can trust a news story.
- Tarkor: A narrative RPG where the world moves on even when you stop.