TruthLens-AI-Fact-Checking-Platform

Inspiration

Misinformation spreads rapidly through social media and messaging platforms, making it difficult for people to identify what is true. We wanted to build an AI-powered platform that makes fact-checking simple, fast, and accessible for everyone.

What it does

TruthLens AI verifies text, images, and videos using specialized AI agents. It analyzes content, searches trusted sources, and provides a verdict, confidence score, explanation, and supporting evidence to help users identify misinformation.

How we built it

We built the frontend using Next.js 15, TypeScript, Tailwind CSS, Framer Motion, and shadcn/ui. The backend is powered by n8n with AI agents using ** Qwen 3.5 Omni Plus, Google Fact Check API, Tavily Search, and ElevenLabs Speech-to-Text*. The frontend is deployed on **Vercel, while the AI workflows run on **Render*.

Challenges we ran into

One of our biggest challenges was designing AI agents that intelligently decide when to use external tools instead of making unnecessary API calls. We also had to handle different content types while ensuring consistent, structured responses for the frontend.

Accomplishments that we're proud of

🚀 Built a multi-agent AI platform for verifying text, images, and videos.
🤖 Integrated multiple AI models and fact-checking APIs into a unified workflow.
☁️ Successfully deployed the frontend on Vercel and the AI backend on Render.
🎨 Developed a modern, responsive user interface with a seamless user experience.

What we learned

This project gave us hands-on experience with Agentic AI, workflow automation using n8n, multimodal AI, prompt engineering, API orchestration, and cloud deployment. Most importantly, we learned that trustworthy AI systems should combine intelligent reasoning with evidence from reliable sources.