Add demo video links to README and BUILD_PLAN

- YouTube: https://youtu.be/U4Dfc7txa_0
- Loom: https://www.loom.com/share/3de27e88e01f4e97bfd13e4f0031f416
- Updated BUILD_PLAN.md to mark demo video as complete
- Added video highlights section
- Only social media post remains for submission

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>

BUILD_PLAN.md

@@ -32,7 +32,7 @@ All major features have been implemented and tested. The application is live on
 - [x] HuggingFace Space deployed
 - [ ] Social media post (LinkedIn/X) published
 - [x] README with complete documentation
-- [ ] Demo video (1-5 minutes)
+- [x] Demo video (1-5 minutes) - [YouTube](https://youtu.be/U4Dfc7txa_0) | [Loom](https://www.loom.com/share/3de27e88e01f4e97bfd13e4f0031f416)
 - [x] All team member HF usernames in Space README
 
 ---
@@ -159,18 +159,23 @@ exporters/
 ---
 
 ### 2.7 Demo Video Production
+
 **Priority:** Critical (Submission Requirement)
-**Status:** ⏳ PENDING
-
-#### Video Content Plan (1-5 minutes):
-1. Introduction (15s) - What is Lineage Graph Accelerator
-2. Problem statement (20s) - Why data lineage matters
-3. Live demo - AI Assistant (30s) - Ask Gemini to generate lineage
-4. Live demo - Sample data (30s) - Use Demo Gallery
-5. Export features (30s) - Export to Collibra/Purview/Atlas
-6. MCP integration (30s) - Show MCP checkbox feature
-7. Real-world use cases (30s) - Enterprise scenarios
-8. Call to action (15s) - Try it on HuggingFace
+**Status:** ✅ COMPLETE
+
+#### Video Links
+
+- **YouTube**: [Watch the Demo](https://youtu.be/U4Dfc7txa_0)
+- **Loom**: [Alternative Link](https://www.loom.com/share/3de27e88e01f4e97bfd13e4f0031f416)
+
+#### Video Highlights (2:30 minutes)
+
+1. Introduction (15s) - Lineage Graph Accelerator overview
+2. AI Assistant (30s) - Google Gemini generating lineage from natural language
+3. MCP Integration (25s) - Local Demo MCP server fetching metadata
+4. Demo Gallery (25s) - Complex 50+ node pipeline + export to Collibra
+5. Interactive Features (20s) - Zoom, PNG/SVG download
+6. Call to Action (15s) - Try on HuggingFace, visit aamanlamba.com
 
 ---
 
@@ -225,9 +230,10 @@ python -m unittest tests.test_app -v
 - [x] MCP integration working
 
 ### Documentation: ✅ COMPLETE
+
 - [x] README.md complete
 - [x] USER_GUIDE.md complete
-- [ ] Demo video - TO DO
+- [x] Demo video - [YouTube](https://youtu.be/U4Dfc7txa_0) | [Loom](https://www.loom.com/share/3de27e88e01f4e97bfd13e4f0031f416)
 - [ ] Social media post - TO DO
 
 ---
@@ -236,7 +242,7 @@ python -m unittest tests.test_app -v
 
 | Task | Priority | Status |
 |------|----------|--------|
-| Record demo video (1-5 min) | **CRITICAL** | ⏳ Pending |
+| ~~Record demo video (1-5 min)~~ | CRITICAL | ✅ Complete |
 | Publish social media post | **CRITICAL** | ⏳ Pending |
 
 ---

DEMO_VIDEO_SCRIPT.md

@@ -0,0 +1,226 @@
+# Demo Video Script - Lineage Graph Accelerator
+## Target: 2-3 minutes | Competition: Gradio Agents & MCP Hackathon Winter 2025
+
+---
+
+## 🎬 SETUP BEFORE RECORDING
+
+### Pre-recording Checklist:
+- [ ] Open HuggingFace Space: https://huggingface.co/spaces/aamanlamba/Lineage-graph-accelerator
+- [ ] Have your Google Gemini API key ready (for AI Assistant demo)
+- [ ] Clear browser cache for clean demo
+- [ ] Close unnecessary tabs/windows
+- [ ] Set screen resolution to 1920x1080 (or 1280x720)
+- [ ] Turn on "Do Not Disturb" mode
+- [ ] Test audio levels
+
+### Recording Tools (Choose One):
+1. **macOS**: QuickTime Player (File → New Screen Recording)
+2. **Free**: OBS Studio (https://obsproject.com)
+3. **Browser**: Loom (https://loom.com) - easiest, records directly
+
+---
+
+## 📝 SCRIPT
+
+### [0:00-0:15] Introduction (15 seconds)
+**[Show the HuggingFace Space with the purple gradient banner visible]**
+
+> "Hi, I'm Aaman Lamba, and this is the Lineage Graph Accelerator - an AI-powered tool that automatically extracts and visualizes data lineage from your data pipelines, built with Gradio 6 and MCP integration."
+
+**ACTION**: Scroll slowly down the page to show the "What You Can Do" section
+
+---
+
+### [0:15-0:35] Problem Statement (20 seconds)
+**[Pause on the features table]**
+
+> "Data engineers and analysts struggle to understand how data flows through their systems. Manual lineage documentation is tedious and quickly becomes outdated. This tool solves that by automatically parsing your dbt manifests, Airflow DAGs, SQL files, and even natural language descriptions."
+
+---
+
+### [0:35-1:05] Feature #1: AI Assistant with Gemini (30 seconds)
+**[Click on "AI Assistant" tab]**
+
+> "Let me show you the AI-powered assistant. I'll paste my Gemini API key and ask it to generate lineage for an e-commerce pipeline."
+
+**ACTION**:
+1. Paste API key into the field
+2. Type in chatbot: "Create a lineage graph for an e-commerce platform with orders, customers, and products tables feeding into a sales mart"
+3. Click Send
+4. Wait for response (should generate JSON)
+5. Click "Use Generated JSON" button
+
+**SAY WHILE WAITING**:
+> "The assistant uses Google Gemini to understand natural language and generate valid lineage JSON automatically."
+
+**AFTER CLICKING "Use Generated JSON"**:
+6. Click "Extract Lineage" button
+7. Show the generated Mermaid graph
+
+> "And there's our interactive lineage graph with color-coded nodes. You can click to zoom in."
+
+---
+
+### [1:05-1:30] Feature #2: MCP Integration (25 seconds)
+**[Click back to "Extract Lineage" tab]**
+
+> "Now let's try the MCP integration - this connects to Model Context Protocol servers for metadata."
+
+**ACTION**:
+1. Check the "Use MCP Server for Metadata" checkbox
+2. Select "Local Demo MCP (Built-in)" from the dropdown
+3. In MCP Query field, type: "ecommerce"
+4. Click "Extract Lineage"
+5. Show the resulting graph
+
+**SAY**:
+> "The MCP server provides pre-configured metadata. This works with any MCP-compatible server on HuggingFace."
+
+---
+
+### [1:30-1:55] Feature #3: Demo Gallery & Export (25 seconds)
+**[Click on "Demo Gallery" tab]**
+
+> "Need inspiration? The Demo Gallery has real-world examples."
+
+**ACTION**:
+1. Click "Load Sample" button for "Complex E-commerce Platform (50+ nodes)"
+2. Show it loading in the text area
+3. Go back to "Extract Lineage" tab
+4. Click "Extract Lineage"
+5. Briefly show the large complex graph
+
+**[Scroll down to Export section]**
+
+> "And you can export to any major data catalog - Collibra, Microsoft Purview, Alation, Apache Atlas, or OpenLineage standard."
+
+**ACTION**:
+1. Select "Collibra" from dropdown
+2. Click "Generate Export"
+3. Show the JSON output briefly
+4. Click "Copy to Clipboard"
+
+---
+
+### [1:55-2:15] Feature #4: Additional Capabilities (20 seconds)
+**[Scroll to show the graph visualization features]**
+
+> "The graphs are fully interactive - click to zoom, download as PNG or SVG, or edit in Mermaid Live."
+
+**ACTION**:
+1. Click on the graph to zoom
+2. Point to the "Download PNG" and "Download SVG" buttons
+3. Point to "Edit in Mermaid Live" link
+
+**SAY**:
+> "All of this supports multiple input formats: dbt, Airflow, SQL DDL, BigQuery, and custom JSON."
+
+---
+
+### [2:15-2:30] Call to Action (15 seconds)
+**[Scroll back up to show the banner with your website link]**
+
+> "This project demonstrates the power of combining Gradio 6, MCP, and AI agents for productivity. Try it yourself on HuggingFace Spaces, check out the full documentation, and visit aamanlamba.com for more projects. Thanks for watching!"
+
+**ACTION**:
+1. Hover over "By Aaman Lamba" button to show it's clickable
+2. Show the HuggingFace Space URL in the browser bar
+3. End recording
+
+---
+
+## 🎯 KEY MESSAGES TO EMPHASIZE
+
+1. **AI-Powered**: Google Gemini integration for natural language lineage generation
+2. **MCP Integration**: Connects to Model Context Protocol servers (competition requirement)
+3. **Multiple Formats**: dbt, Airflow, SQL, BigQuery, JSON
+4. **Enterprise Ready**: Exports to 5 major data catalogs
+5. **Gradio 6**: Modern, professional UI (competition requirement)
+6. **Real-World Impact**: Solves actual data governance problems
+
+---
+
+## ✅ POST-RECORDING
+
+1. **Review the video**:
+   - Check audio quality
+   - Ensure all features are clearly visible
+   - Verify timing is under 5 minutes (ideally 2-3 min)
+
+2. **Edit if needed**:
+   - Trim any long pauses
+   - Add title card (optional): "Lineage Graph Accelerator | Gradio + MCP Hackathon 2025"
+   - Add your website URL as overlay at the end (optional)
+
+3. **Export settings**:
+   - Format: MP4
+   - Resolution: 1080p (1920x1080) or 720p (1280x720)
+   - Frame rate: 30fps
+   - Bitrate: At least 5 Mbps for good quality
+
+4. **Upload**:
+   - YouTube (recommended - can embed in README)
+   - Loom (easiest, shareable link)
+   - Google Drive (make sure it's publicly accessible)
+
+5. **Update README.md**:
+   - Add video link under "Demo Video" section
+   - Update BUILD_PLAN.md to mark video as complete
+
+---
+
+## 💡 RECORDING TIPS
+
+### DO:
+- Speak clearly and at moderate pace
+- Show each feature for at least 5 seconds
+- Let visual changes complete before moving on
+- Smile while talking (it affects your voice tone!)
+
+### DON'T:
+- Rush through features
+- Use filler words ("um", "uh", "like")
+- Apologize for anything
+- Go over 5 minutes (judges won't watch it all)
+
+### IF SOMETHING GOES WRONG:
+- Pause, take a breath, and continue from that section
+- You can edit out mistakes later
+- Or just re-record that section
+
+---
+
+## 🎥 EASIEST RECORDING METHOD (Loom)
+
+1. Install Loom browser extension: https://loom.com
+2. Click Loom icon → "Start Recording"
+3. Select "Screen + Camera" (or just "Screen Only")
+4. Choose "Current Tab"
+5. Click "Start Recording"
+6. Follow the script above
+7. Click "Stop" when done
+8. Loom auto-uploads and gives you a shareable link
+9. Download the MP4 if needed
+
+**Total time: 5-10 minutes including setup!**
+
+---
+
+## 📊 SUGGESTED TIMELINE
+
+| Time | Section | Key Action |
+|------|---------|------------|
+| 0:00 | Intro | Show banner, introduce yourself |
+| 0:15 | Problem | Explain data lineage challenge |
+| 0:35 | AI Assistant | Demo Gemini chatbot generating lineage |
+| 1:05 | MCP | Show MCP server integration |
+| 1:30 | Demo Gallery | Load complex sample + export |
+| 1:55 | Features | Interactive graph, downloads |
+| 2:15 | CTA | Website link, HF Space, thank you |
+
+**Total: ~2.5 minutes** ✅
+
+---
+
+Good luck with the recording! 🎬

README.md

@@ -279,7 +279,16 @@ python test_setup.py
 
 ### Demo Video
 
-[Link to demo video - Coming Soon]
+📺 **YouTube**: [Watch the Demo](https://youtu.be/U4Dfc7txa_0)
+🎥 **Loom**: [Alternative Link](https://www.loom.com/share/3de27e88e01f4e97bfd13e4f0031f416)
+
+**Highlights**:
+
+- AI Assistant with Google Gemini generating lineage from natural language
+- MCP Integration with Local Demo server
+- Demo Gallery with 50+ node complex pipelines
+- Export to Collibra, Purview, and Apache Atlas
+- Interactive Mermaid visualizations with zoom and download
 
 ### Social Media Post
 

YOUTUBE_DESCRIPTION.md

@@ -0,0 +1,183 @@
+# YouTube Description for Lineage Graph Accelerator Demo
+
+---
+
+## Title Options:
+
+**Option 1 (Recommended):**
+Lineage Graph Accelerator - AI-Powered Data Lineage with Gradio 6 & MCP
+
+**Option 2:**
+Automate Data Lineage Extraction with AI | Gradio Agents & MCP Hackathon 2025
+
+**Option 3:**
+Data Lineage Made Easy: Gradio 6 + Google Gemini + MCP Integration
+
+---
+
+## Description:
+
+```
+🚀 Lineage Graph Accelerator - AI-Powered Data Lineage Extraction & Visualization
+
+Tired of manually documenting data pipelines? This tool automatically extracts and visualizes data lineage from dbt, Airflow, SQL, BigQuery, and more - powered by Gradio 6, Google Gemini AI, and Model Context Protocol (MCP).
+
+Built for the Gradio Agents & MCP Hackathon - Winter 2025 🎂
+
+🔗 Try it Live: https://huggingface.co/spaces/aamanlamba/Lineage-graph-accelerator
+
+✨ Key Features:
+• AI Assistant: Generate lineage from natural language using Google Gemini
+• MCP Integration: Connect to Model Context Protocol servers for metadata
+• Multiple Input Formats: dbt manifests, Airflow DAGs, SQL DDL, BigQuery, custom JSON
+• Interactive Visualizations: Mermaid diagrams with zoom, PNG/SVG export
+• Enterprise Export: OpenLineage, Collibra, Microsoft Purview, Alation, Apache Atlas
+• Demo Gallery: Pre-built samples with 50+ node complex pipelines
+
+🎯 Real-World Impact:
+Solve data governance and compliance challenges by automatically documenting data flows across your entire data platform. Perfect for data engineers, analysts, and compliance teams.
+
+📚 Documentation:
+• GitHub: https://github.com/aamanlamba/lineage-graph-accelerator
+• User Guide: Full documentation included
+• Author: https://aamanlamba.com
+
+🏆 Competition:
+Gradio Agents & MCP Hackathon - Winter 2025
+Track 2: MCP in Action (Productivity)
+Celebrating MCP's 1st Birthday!
+
+🛠️ Tech Stack:
+• Gradio 6.0 - Modern UI framework
+• Google Gemini API - AI-powered lineage generation
+• Model Context Protocol - Metadata extraction
+• Mermaid.js - Interactive graph visualization
+• Python - Backend processing
+
+💡 Use Cases:
+✓ Data governance and compliance documentation
+✓ Impact analysis for data changes
+✓ Onboarding new team members to complex pipelines
+✓ Migration planning and data catalog integration
+✓ Automated lineage for CI/CD pipelines
+
+📊 What You'll See in This Demo:
+0:00 - Introduction & Problem Statement
+0:35 - AI Assistant (Gemini) generating lineage from natural language
+1:05 - MCP Integration with Local Demo server
+1:30 - Demo Gallery with complex samples
+1:55 - Export to data catalogs (Collibra, Purview, Atlas)
+2:15 - Interactive features & Call to Action
+
+🔔 Subscribe for more AI + Data Engineering tools!
+
+#Gradio #MCP #DataLineage #AI #DataEngineering #GoogleGemini #HuggingFace #DataGovernance #Hackathon #Python #DataCatalog #MLOps #Analytics
+```
+
+---
+
+## Tags (if uploading to YouTube):
+
+```
+gradio, mcp, data lineage, google gemini, ai, data engineering, huggingface, model context protocol, data governance, data catalog, dbt, airflow, sql, bigquery, collibra, purview, alation, atlas, openlineage, python, machine learning, mlops, data analytics, hackathon, gradio 6
+```
+
+---
+
+## Thumbnail Ideas (if you want to create one):
+
+**Text Overlay:**
+```
+LINEAGE GRAPH
+ACCELERATOR
+AI-Powered | Gradio 6 | MCP
+```
+
+**Visual Elements:**
+- Screenshot of the purple gradient banner
+- Screenshot of a complex lineage graph
+- "AI-Powered" badge
+- Your photo or avatar
+- HuggingFace logo
+
+**Colors:**
+- Purple gradient (#667eea to #764ba2)
+- White text
+- High contrast for readability
+
+---
+
+## Social Media Snippet (for embedding):
+
+```
+🚀 Just launched Lineage Graph Accelerator for the Gradio Agents & MCP Hackathon!
+
+✨ AI-powered data lineage extraction with:
+• Google Gemini natural language generation
+• MCP integration for metadata
+• Export to Collibra, Purview, Atlas
+• Interactive Mermaid visualizations
+
+🔗 Try it: https://huggingface.co/spaces/aamanlamba/Lineage-graph-accelerator
+🎥 Demo: [YouTube Link]
+
+#Gradio #MCP #DataLineage #AI
+```
+
+---
+
+## LinkedIn Post Version:
+
+```
+🚀 Excited to share my submission for the Gradio Agents & MCP Hackathon - Winter 2025!
+
+Introducing: **Lineage Graph Accelerator** - An AI-powered tool that automatically extracts and visualizes data lineage from modern data platforms.
+
+🎯 The Problem:
+Data engineers spend hours manually documenting data pipelines. Documentation quickly becomes outdated. Impact analysis requires tribal knowledge.
+
+💡 The Solution:
+Automated lineage extraction from dbt, Airflow, SQL, BigQuery + natural language using Google Gemini AI, powered by Model Context Protocol (MCP) and Gradio 6.
+
+✨ Key Features:
+• AI Assistant for generating lineage from descriptions
+• MCP integration for real-time metadata
+• Export to Collibra, Microsoft Purview, Alation, Apache Atlas
+• Interactive visualizations with zoom and export
+• 50+ node complex pipeline support
+
+🔗 Try it live: https://huggingface.co/spaces/aamanlamba/Lineage-graph-accelerator
+🎥 Demo video: [YouTube Link]
+💻 GitHub: https://github.com/aamanlamba/lineage-graph-accelerator
+
+Built with: #Gradio #MCP #GoogleGemini #Python #DataEngineering
+
+Thanks to @Hugging Face, @Gradio, and @Anthropic for hosting this amazing hackathon! 🎂
+
+What data governance challenges are you facing? Let me know in the comments!
+
+#DataLineage #AI #DataGovernance #DataEngineering #MLOps #HuggingFace #Hackathon
+```
+
+---
+
+## X/Twitter Post Version:
+
+```
+🚀 Just shipped Lineage Graph Accelerator for the @Gradio + MCP Hackathon!
+
+AI-powered data lineage extraction with:
+✨ @Google Gemini natural language generation
+✨ MCP integration
+✨ Export to Collibra, Purview, Atlas
+✨ Interactive graphs
+
+🔗 Try it: https://huggingface.co/spaces/aamanlamba/Lineage-graph-accelerator
+🎥 Demo: [YouTube Link]
+
+#Gradio #MCP #DataLineage #AI
+```
+
+---
+
+Copy any of these and customize as needed! The YouTube description includes all important links, features, and is optimized for search. 🎬