Multi-model agent orchestration, LLM evaluation, prompt engineering, and production AI workflows. I don't just use AI tools — I architect the systems behind them, and I evaluate output because 20 years of building taught me what correct looks like.
"I evaluate AI output because I know what correct looks like. When a model generates code, designs, or analysis, I can tell whether it's right — not because I ran a test suite, but because I've spent 20 years building the same kinds of systems by hand. That judgment is what separates AI operators from AI architects."
Daily workflow spanning GPT-4o, o1, o3, Claude, Grok, and Gemini. Each model selected for its strengths — reasoning, creative generation, code review, evaluation — and composed into coherent pipelines.
Built WAP (multi-persona AI agent platform) and run production autonomous agents across multiple workspaces. Agents handle brand development, project management, infrastructure, and client communication.
System prompt architecture, chain-of-thought design, persona crafting, and evaluation frameworks. Every agent I deploy has carefully engineered prompts calibrated through iterative testing.
DALL-E, Midjourney, and generative workflows integrated into production creative pipelines. AI-generated assets that meet professional art direction standards — because I'm also an Art Director.
Deep experience with the OpenAI API ecosystem: Chat Completions, Assistants, function calling, vision, DALL-E, embeddings. Custom Vercel gateway routing to OpenAI services.
Code review, design critique, content evaluation, and quality assurance for AI-generated outputs. Two decades of domain expertise across engineering, art, and product make me a rigorous evaluator.
Every skill here is backed by real project experience — speccing, documenting, directing, and hands-on production. The meter shows depth of mastery, not whether I can do it.
Custom-built AI platform with multiple specialized personas, each with distinct system prompts, capabilities, and evaluation criteria. Orchestrates complex workflows across different AI models.
Runs two autonomous AI agents across workspaces coordinating brand development, project management, and infrastructure for 5+ simultaneous client engagements at ironreach.com. Real production AI, not a demo.
Integrated AI-driven systems into game architecture. Applied machine learning concepts to gameplay mechanics, balancing, and content generation within a production game environment.
I bring two decades of cross-domain expertise to AI evaluation, system design, and agent architecture.