The Experiments Lab
Where curiosity meets code. Real exploratory R&D into local LLMs, embedded IoT, computer vision, spatial computing, and autonomous agents:
Offline Local LLMs & Embedded Inference
Can an organization run zero-data-leakage intelligence models completely offline without sending enterprise data to external cloud APIs?
Benchmarked quantized Llama 3 & Mistral models running on local Apple Silicon & Linux edge servers with custom vector databases (ChromaDB).
“Local quantized models are now fast enough to replace cloud APIs for 70% of routine corporate document processing tasks.”
ESP32 Environmental & Attendance Sensor Node
How to automate smart classroom attendance and indoor air quality telemetry without high-cost proprietary hardware?
Engineered an ultra-low-cost ESP32 microcontroller with RFID reader, temperature/CO2 sensors, and MQTT transmission directly to school ERP.
“Hardware edge computing combined with lightweight MQTT protocols can reduce smart classroom infrastructure costs by over 75%.”
Real-Time Object & Gesture Detection on Edge
Can low-cost webcams turn any standard projector screen into an interactive digital smartboard via real-time computer vision?
Built OpenCV and MediaPipe pipelines in Python to track optical laser pointers and hand gestures, translating coordinates into digital whiteboard strokes.
“Computer vision can democratize smart classroom technology for rural schools with zero requirement for costly capacitive touch panels.”
Interactive WebXR Physics Playground
How to make complex atomic orbitals and gravitational physics accessible directly inside a web browser without installing 5GB apps?
Developed interactive WebXR 3D simulations utilizing Three.js and Cannon.js physics engines with full mobile and VR headset support.
“Spatial interactivity dramatically reduces cognitive load when learning 3D geometric and physics concepts compared to static 2D diagrams.”
Self-Healing Workflow & Research Agent
Can an autonomous AI agent monitor regulatory filings, summarize changes, and alert compliance teams without human initiation?
Created an asynchronous LangChain/LangGraph agent pipeline that scrapes regulatory updates, validates changes with structured LLM schemas, and dispatches structured digests.
“Deterministic guardrails around probabilistic LLM agents are essential for enterprise compliance workflows.”
