The latest articles on DEV Community by Lou Vincent Baroro (@devlou). https://dev.to/devlou https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4032308%2Fb4c8d563-5216-4053-ad12-032414134e20.jpg https://dev.to/devlou en Lou Vincent Baroro Thu, 16 Jul 2026 15:04:36 +0000 https://dev.to/devlou/how-we-built-a-neuro-symbolic-ai-platform-for-the-asean-ai-hackathon-2026-909 https://dev.to/devlou/how-we-built-a-neuro-symbolic-ai-platform-for-the-asean-ai-hackathon-2026-909 <p><em>Originally published on my personal engineering blog at <a href="https://louvincentbaroro.me/blog/asean-ai-hackathon" rel="noopener noreferrer">louvincentbaroro.me</a>.</em></p> <p>At the <strong>ASEAN AI Hackathon 2026</strong>, our team Syntaxure SEA set out to solve a massive problem in Southeast Asia: <strong>Environmental accountability.</strong> </p> <p>Citizens witness environmental violations every day. Illegal logging, open burning, and hazardous waste are rampant. But reporting is fragmented, and whistleblowing is dangerous. </p> <p>To solve this, we built <strong>LikasLens</strong>, a neuro-symbolic civic intelligence platform that allows citizens to snap photos of violations, dynamically routes them to the correct government agency using AI, and protects the whistleblower's identity.</p> <h2> Advanced Platform Features </h2> <p>LikasLens is far more than just a reporting tool. Some of the most complex features we engineered include:</p> <ol> <li>**Eco-Credit Rewards System: Users earn points for verified reports that can be redeemed at major partner stores (e.g., proposed integrations with SM, Jollibee, Globe).</li> <li> <strong>Report Chaining &amp; Anti-Sybil Logic:</strong> We implemented GPS-proximity clustering. If multiple users report the same issue within a 50m radius, the system corroborates and auto-escalates it.</li> <li> <strong>Pattern Escalation:</strong> The platform detects spatial-temporal patterns to trigger urgent responses for repeated violations in the same barangay.</li> <li> <strong>Neo4j GraphRAG Integration:</strong> The system auto-detects the exact jurisdiction and law violated based on the user's country using AI.</li> </ol> <h2> The Engineering Architecture </h2> <p>Building a platform of this magnitude required extreme focus. My partner Jeff Martinez and I split the architecture perfectly down the middle.</p> <p>I was responsible for architecting the entire user-facing structure and interactive systems using a <strong>Next.js 16 Monorepo</strong>. My core focus included:</p> <ul> <li> <strong>Interactive Data Visualization:</strong> Engineering MapLibre GL heatmaps and 3D interactive globes (cobe.js) to visualize violation hotspots.</li> <li> <strong>Blockchain UI:</strong> Building the frontend for SHA-256 evidence hashing to ensure a tamper-proof chain of custody.</li> <li> <strong>Multi-Language Structure:</strong> Laying out the <code>next-intl</code> localization structure for 10 ASEAN languages.</li> </ul> <p>Meanwhile, Jeff engineered the <strong>Laravel 12 backend</strong> and Python/FastAPI microservices, integrating dual YOLOv8 vision models and ONNX Runtime WebAssembly directly into the mobile flow.</p> <h2> The Results </h2> <p>Out of hundreds of teams, we finished as <strong>Semi-Finalists (Top 40 Overall)</strong> and placed in the <strong>Top 10 for the Climate Track</strong>.</p> <p>While we barely missed the grand prize (a flight to Vietnam), we walked away with a piece of engineering that proves exactly what we are capable of. We built a massive, enterprise-grade neuro-symbolic platform capable of handling multi-language support, blockchain hashing, and jurisdiction-aware AI routing. </p> <p><em>If you want to read more of my engineering notes or check out my other AI projects, visit my portfolio at <a href="https://louvincentbaroro.me" rel="noopener noreferrer">louvincentbaroro.me</a>.</em></p> ai architecture machinelearning showdev