Benchmark: add LLM-as-a-Judge + BERTScore (hackathon 30% accuracy criterion)

Branding: replace Claude with TigerGraph logo and remove Claude references

Fix UI: 3-pipeline playground, science examples, correct docs/architecture

Improve latency: parallel LLM calls, embedding cache, client reuse

Add .gitignore, dataset metadata, retrieval layer, and latest web/graphrag updates

Fix #8: Update web API compare route — 3-pipeline (LLM-Only + Basic RAG + GraphRAG) with side-by-side metrics

🎨 Ultra premium UI: 6 separate pages with animations, bento grid, premium design

🎨 New multi-section home page

🎨 Update layout with new title

🎨 Ultra premium UI: enhanced design system with animations, gradients, bento grid

Add benchmark API route for live benchmark runs from dashboard

Add multi-provider compare API route + providers listing endpoint

Add providers listing API endpoint

Add Claude-powered compare API route with dual-pipeline orchestration

Add main page with hero, navbar, and tab controller

Add root layout with font loading and metadata

Add global CSS with TigerGraph\u00d7Claude fused design system