Rudy Martinez – Prompt Engineer

Exploring LLMs, building better prompts, and testing model behavior at scale.

About Me

I'm currently learning Python and diving deep into large language models (LLMs). I run over 30 models locally using LM Studio and design evaluation rubrics to test prompt behavior across domains like math, storytelling, science, and research.

My goal is to build thoughtful AI tools that go beyond hype—and share what I learn along the way.

Blog

Lab Notes

Here you’ll find updates, experiments, and commentary on my prompt engineering journey.

Projects

LLM Prompt Evaluation Lab

A collection of test prompts run through 30+ local models, with performance notes, screenshots, and a rubric developed across multiple use cases.

Prompt Cookbook

A growing library of tested prompts for summarization, instruction following, creativity, and more—optimized for OpenAI, Claude, DeepSeek, and others.

Contact

Email me at: rudy@simplesolutions.technology

GitHub: Chicano In Paris