Journal

Field notes.

Short essays on building interfaces, shaping motion, and putting machine learning to work without the hype.

Prompt Engineering12 min read

How to Write Prompts That Produce Useful AI Output

A practical framework for turning vague AI requests into clear, testable instructions—with reusable templates, examples, and a quality checklist.

Machine Learning16 min read

Fine-tuning gpt-oss-120b with LoRA: A Practical Guide

A realistic workflow for adapting gpt-oss-120b with LoRA—from deciding whether to fine-tune through data design, memory planning, evaluation, and deployment.

Computer Vision14 min read

Reasoning-First OCR with Multimodal LLMs

A production-minded guide to extracting structured data from complex documents with traditional OCR, multimodal LLMs, strict schemas, validation, and human review.

MLOps13 min read

Building AI Pipelines That Stay Reliable in Production

A practical blueprint for dependable AI pipelines: explicit contracts, reproducible training, safe deployment, useful monitoring, and simple operations.