VeriGen AI

Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

About VeriGen AI is an Autonomous Multi-Agent Research & Fact Verification System developed for InnovaHack 2026 – Domain 3: Generative AI.

Instead of relying on a single Large Language Model (LLM), VeriGen AI coordinates multiple specialised AI agents that independently research, verify, analyse contradictions, and generate trustworthy, citation-backed reports with confidence scores.

Our goal is to reduce AI hallucinations and improve transparency by validating every important claim against multiple trusted sources before presenting it to the user.

🚨 Problem Statement Generative AI models are powerful research assistants but often produce hallucinations, unsupported claims, and misinformation.

Users frequently receive answers that appear convincing but lack reliable evidence or citations, making them unsuitable for research, education, healthcare, finance, and other critical domains.

The challenge is to design a system where multiple AI agents collaborate to:

Research information Cross-verify claims Detect contradictions Identify hallucinations Provide reliable citations Generate confidence scores 💡 Our Solution VeriGen AI introduces a Multi-Agent Verification Pipeline where specialised AI agents work collaboratively instead of relying on a single AI model.

Each agent performs one dedicated task:

Research trusted sources Verify extracted claims Detect contradictions Identify hallucinations Calculate confidence scores Generate a final evidence-backed report This collaborative workflow significantly improves the reliability and transparency of AI-generated information.

🚀 Key Features ✅ Autonomous Multi-Agent Architecture

✅ Real-Time Deep Research

✅ Fact Verification

✅ Hallucination Detection

✅ Contradiction Analysis

✅ Confidence Score Generation

✅ Citation-backed Reports

✅ Research History

✅ Google Authentication

✅ PDF Upload Support

✅ URL Verification

✅ Voice Search

✅ Dashboard Analytics

✅ Saved Reports

🧠 Multi-Agent Workflow User Query │ ▼ Orchestrator Agent │ ▼ Research Agent │ ▼ Verification Agent │ ▼ Contradiction Detector │ ▼ Synthesis Agent │ ▼ Final Report ⚙️ Tech Stack Frontend React.js Next.js Tailwind CSS Backend Node.js Express.js Database Supabase AI Agent Framework Lyzer AI Deployment Vercel

What we learned

What's next for VeriGen AI

Built With

• css3
• express.js
• next
• node.js
• react
• tailwind