Back

LikasLens: Architecting an AI-Powered Civic Platform for the ASEAN Hackathon

At the ASEAN AI Hackathon 2026, my partner Jeff Martinez (Backend/AI) and I (Frontend/UI) set out to solve a massive problem in Southeast Asia: Environmental accountability.

Citizens witness environmental violations every day. Illegal logging, open burning, and hazardous waste are rampant. But reporting is fragmented across borders, and whistleblowing is dangerous.

To solve this, we built LikasLens, 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.

Advanced Platform Features

LikasLens is far more than just a reporting tool. It is a complete ecosystem designed to drive civic engagement. Some of the most complex features we engineered include:

  1. Eco-Credit Rewards System: To incentivize reporting, we built a fully functional rewards economy. Users earn points for verified reports and unlock achievements that can be redeemed at major partner stores (SM, Jollibee, Globe, 7-Eleven).
  2. Report Chaining & Anti-Sybil Logic: We implemented GPS-proximity clustering. If multiple users report the same issue within a 50m radius, the system corroborates and auto-escalates it. To prevent spam, we built a strict 5m Anti-Sybil geofence.
  3. Pattern Escalation: The platform detects spatial-temporal patterns. For example, if 5 illegal dumping reports occur in the same barangay within 48 hours, the system automatically triggers an urgent escalation.
  4. Likasy AI Chatbot: A Gemini-powered legal assistant built directly into the app that answers citizen questions about their rights and local environmental laws.
  5. REDD+ MRV Eligibility: The system automatically flags severe deforestation reports to make them eligible for international carbon credit mechanisms (REDD+).

The Engineering Divide

Building a platform of this magnitude required extreme focus. We split the architecture perfectly down the middle to tackle the massive scope.

The Frontend, PWA, & Architecture Structure (My Role)

I was responsible for architecting the entire user-facing structure, layouts, and interactive systems. I built the Next.js 16 Monorepo, which included the Public Dashboard, Admin Portal, and the Mobile PWA.

My core focus was delivering a hyper-premium UI/UX and laying down the structural foundation for our advanced features:

  1. Interactive Data Visualization: I engineered the MapLibre GL heatmaps and the 3D interactive globes (cobe.js) to visualize violation hotspots and chained reports.
  2. Blockchain & Rewards UI: I built the frontend architecture for the Rewards catalog and the UI flows that interact with the SHA-256 evidence hashing for our tamper-proof chain of custody.
  3. Multi-Language Structure: I laid out the next-intl localization structure, ensuring the UI could seamlessly render all 10 ASEAN languages.
  4. Camera & Triage UI: I built the mobile camera scanning interfaces and the Ghost Mode layouts, ensuring whistleblowers felt completely secure.

The Backend & Neural Connections (Jeff Martinez)

Once I built the frontend structures, Jeff wired them into his massive backend infrastructure.

He engineered the Laravel 12 backend and the Python/FastAPI microservice. When a user clicks the camera scan button I built, Jeff's backend takes over and runs the image through dual YOLOv8 vision models and ONNX Runtime WebAssembly.

Jeff also integrated the Neo4j GraphRAG pipeline, taking the multi-language data from the frontend and auto-detecting the exact jurisdiction and law violated based on the user's country.

The Reality of the Results

Out of hundreds of teams, we finished as Semi-Finalists (Top 40 Overall) and placed in the Top 10 for the Climate Track.

To be completely honest, our goal wasn't just to build a cool project. We joined this hackathon for one specific reason: a free flight to Vietnam. If we had just secured a spot in the Top 4 for the Climate Track, we would have been on that plane. Missing out on that trip by such a narrow margin still haunts me.

It is a tough pill to swallow. But looking back at the sheer scale of what Jeff and I accomplished in that time frame, I realize that the engineering itself wasn't a waste. We didn't just build a hackathon prototype. We built a massive, enterprise-grade neuro-symbolic platform with multi-language support for 10 nations, blockchain hashing, eco-credit economies, and jurisdiction-aware law routing.

We didn't get the flight to Vietnam, but we walked away with a piece of engineering that proves exactly what we are capable of.