Overview

Welcome to the Community Agentic Arena! This competition challenges you to build a Retrieval-Augmented Generation (RAG) AI agent in n8n that can accurately answer questions based on a provided PDF knowledge base. Over $10,000 in prizes await!

What You're Building

You'll create an n8n workflow that:

• Ingests PDF documents into a vector database or knowledge retrieval system
• Processes natural language questions about the content
• Returns accurate answers based solely on the provided documentation with proper citations
• Demonstrates high accuracy when tested against our evaluation questions

Submission Requirements

• Format: MP4 video, maximum 2 minutes, under 100MB
• Content: Your video must clearly show:
  1. Your n8n workflow architecture
  2. The RAG system processing evaluation questions
  3. Your final accuracy scores/results
• Submit via this webpage (runs on n8n!)

Rules

Eligibility

• Open to all n8n community members
• One winning submission per person - you can try again if the submission does not win
• Must use n8n for the workflow implementation

Judging Criteria

Submissions will be scored on:

• Voice over: Thoroughly explain your workflow and say your eval results out loud
  • The first round of judging is based on the transcription, SO THIS IS REQUIRED TO PASS