import './Hero.css' const codeSnippet = `curl -X POST https://api.fairrelay.io/v1/consolidate \\ -H "x-api-key: fr_live_••••••••••••" \\ -H "Content-Type: application/json" \\ -d '{ "shipments": [ { "id": "sh_001", "pickupLat": 19.07, "pickupLng": 72.87, "dropLat": 18.52, "dropLng": 73.85, "weight": 500, "volume": 2.0, "timeWindowEnd": "2026-05-14T18:00" }, { "id": "sh_002", "pickupLat": 19.08, "pickupLng": 72.88, "dropLat": 18.53, "dropLng": 73.86, "weight": 300, "volume": 1.5, "timeWindowEnd": "2026-05-14T18:00" } ], "trucks": [ { "id": "trk_1", "maxWeight": 2000, "maxVolume": 8.0 } ] }'` const responseSnippet = `{ "groups": [ { "groupId": 1, "truckId": "trk_1", "shipments": ["sh_001", "sh_002"], "utilizationWeight": 82.5, "confidence": 91 } ], "metrics": { "utilizationBefore": 27.1, "utilizationAfter": 82.5, "tripsReduced": 3, "tripReductionPercent": 50, "carbonSavedKg": 14.2, "optimizationScore": 87 } }` export default function Hero() { return (
{/* Background glows */}
LoRRI AI Hackathon 2026 · PS#4 + PS#5

AI Load Consolidation
&{' '} Route Optimization

India's logistics networks transport 60% of shipments with partially filled vehicles. FairRelay's 5-agent AI pipeline intelligently groups shipments, maximizes vehicle utilization, and optimizes multi-stop routes — reducing trips, cost, and carbon emissions.

27% → 82% Vehicle utilization
50% Trips reduced
14.2 kg CO₂ saved/run
{/* Problem Statement Context */}

Novelty: Two Problem Statements Combined

PS#5 AI Load Consolidation (primary) + PS#4 AI Route Optimization (novelty). 5 AI agents orchestrated by LangGraph with OR-Tools CP-SAT solver, K-Means clustering, and Q-learning RL — all integrated into LoRRI production via API.

{[['🧠 5 AI Agents', 'LangGraph'], ['⚙️ OR-Tools', 'CP-SAT Solver'], ['📊 scikit-learn', 'KMeans'], ['🔄 RL Agent', 'Q-Learning']].map(([num, label]) => ( {num} {label} ))}
POST /v1/consolidate
                {codeSnippet}
              
200 OK · 312ms
                {responseSnippet}
              
{/* Scroll indicator */}
) }