Thirty years of editorial judgment applied to writing, research, and AI-generated content.
For more than three decades, I have helped evaluate, edit, and improve written communication across journalism, corporate communications, technology, SEO, and digital publishing.
Today, I apply those same editorial principles to AI-generated content.
This site showcases my work evaluating AI responses for factual accuracy, reasoning, instruction-following, clarity, audience fit, and overall quality. It also highlights the editorial process behind improving prompts, refining outputs, identifying hallucinations, and producing content that better serves its intended audience.
The case studies and investigations published here are drawn from real-world writing, editing, research, and AI evaluation projects. Each demonstrates a structured approach to assessing quality, explaining decisions, and improving outcomes through careful human judgment.
Whether the task is reviewing an AI-generated response, editing a résumé, fact-checking a sports feature, refining a prompt, or comparing the performance of different language models, the objective is always the same:
Produce information that is more accurate, more useful, and more trustworthy.
---------------------------------------------------
AI Evaluation
Editorial Investigations
Hallucination Autopsies
Editorial QA
Prompt Refinement
[Learn More]
---------------------------------------------------
Writing Portfolio
Journalism
Technology
Corporate Storytelling
Sports
SEO
[View Portfolio]
---------------------------------------------------
Editorial Philosophy
How I evaluate writing, reasoning and AI outputs
---------------------------------------------------
Contact