ARTICLES
Longer write-ups on projects I have built: machine learning for forests and health, language technology for Ewe, and coding agents. Each one covers how it works, what the numbers say, and what went wrong.

Edge AI, Audio ML, YAMNet
EchoForest: Listening for Chainsaws in Ghana's Forests
The full story of EchoForest, an acoustic machine-learning system that runs on Raspberry Pi sensor nodes and alerts rangers to illegal logging, from a 2021 hackathon win to my final-year project.
6 min read

LLM, Fine-tuning
Adapting a 2B Language Model to Health on a Free GPU
How I fine-tuned Qwen3.5-2B-Base on open health text and medical Q&A with LoRA on a Colab T4, and what the held-out numbers actually say.
7 min read

NLP, Low-resource languages
Teaching a Computer to Read Ewe: An N-Gram Language Model From Scratch
I built unigram to 5-gram language models for Ewe using nothing but counting and arithmetic. The results were useful. The bugs I hit on the way were more useful.
8 min read

AI Agents, Claude Agent SDK
Mesora Blocks: Building a Team of Coding Agents That Turn Plain Words Into Running APIs
How my team and I designed a multi-agent system on the Claude Agent SDK that lets a non-developer describe a backend and get back a running, tested API, and why the most important parts of it are not AI at all.
8 min read