Building AI systems that solve real operational problems.
I'm Sai, an Applied AI and GenAI engineer in Thailand writing about agentic systems, computer vision, edge AI, Geospatial AI, and shipping under real constraints.
Diamond answers Bhutan Airlines visitors from a bounded packet of site pages, drops citations that were not retrieved, and hands off when the pages do not support the claim.
CareerBot is an open-source MCP toolkit that scores jobs against a Master CV, drafts checked resumes, and saves SHA-256 snapshots. It does not scrape boards or submit applications.
Reproducing OpenAI's Parameter Golf language model training challenge on RunPod — covering environment setup, SSH debugging, dataset wiring, and landing a val_bpb baseline on a single H100.
A walkthrough of reproducing a working CLIP image-to-text retrieval baseline on XR2 Gen 2, covering environment fixes, SSL certificates, dataset paths, and preprocessing gotchas.
A first-time thesis writer, not a strong coder, built an open-source AI agent system that helped him publish in a Q1 journal and defend his thesis. This is the full story.
After 8 GSD levels, 6 models, and 3,368 tile-label pairs, here's the condensed operational guide for deploying AI-based oil palm monitoring with a drone.
A segmentation mask is a collection of pixels. Here's how we convert that into a physical canopy area in square metres and an equivalent diameter — with the full derivation and error analysis.
I trained YOLOv8, YOLOv11, Mask R-CNN, and two SAM hybrid pipelines on oil palm drone data. Here's what the numbers actually showed — including the result that surprised me most.
How I built a multi-resolution oil palm segmentation dataset from scratch — including the 301 corrupted label files I had to fix before anything could run.
A model trained at 3cm resolution failed at 6cm. Same drone. Same plantation. Different altitude. Here's the physics and math behind why — and what to do about it.
An open-source Obsidian plugin that converts wiki-links, image embeds, and callouts to Jekyll-compatible Markdown — then copies everything to your _posts/ folder.
From zero to a fully-featured minimalist blog using Jekyll, GitHub Pages, and AI pair programming. A transparent look at ethical AI-assisted development.
A bounded Python and MCP toolkit for scoring job fit, preparing verified application artifacts, and tracking state with immutable snapshots — not unattended job-board automation.
