VeriCrisis is an AI-powered agent designed to detect, verify, and correct misinformation during global and local crises. The system continuously scans multiple data sources — including news outlets, social media, and public statements — to identify emerging claims and assess their credibility in real time.

Built on FastAPI, VeriCrisis functions as a scalable backend service. It leverages Perplexity and Google’s Gemini 2.0 Flash for multi-source verification, cross-referencing claims with reliable information to compute a confidence score and provide clear verdicts such as True, Misleading, or False.

The verified results and insights are stored using Supabase, ensuring persistent access to claim histories and transparency. The system can also generate contextual summaries and corrective explanations, helping users and organizations quickly understand what’s true and what’s not — especially in high-stakes crisis situations where misinformation spreads fastest.

Ultimately, VeriCrisis aims to serve as a trustworthy AI fact-checking backbone that empowers decision-makers, media platforms, and the public with accurate, real-time information.