What I do

What I work on

Three things, every day. All three are flavors of the same underlying question: how do you make AI actually useful?

🤖

Applied AI products & agents

AI that does a job end-to-end: not chatbots that answer questions, but agents that take a task, break it into steps, call tools, handle errors, and deliver a result. Voice agents on live calls. Research agents that synthesize reports. Workflow agents that replace a whole job function.

When does an agent work? When does it fail? How do you know before you ship?

🔧

LLM integration & prompt engineering

Foundation models (Claude, GPT, Gemini) are the engines. The interesting work is the plumbing: retrieval architectures, prompt caching, agent orchestration, evaluation pipelines, tool-use error handling.

My takeaways live in Prompting for agents and the Patterns section.

🧭

AI advisory

Founders and operators ask me to look at their AI architecture. The goal is always the same: an honest second opinion. Am I overbuilding? Am I overselling the AI? Is there a simpler path?

If you want that, get in touch.

The through line: all three are about the product layer. Not training models. Not pushing benchmarks. Just making AI do real things for real people.

Topics

Areas I go deep on

LLM agents Voice AI RAG systems Prompt engineering Claude API OpenAI API MCP servers Automation pipelines Autonomous systems Agent evaluation Tool-use design Prompt caching

Want this pointed at your business?

I build one system at a time, flat price, in accounts you own. Start with the workflow that eats the most hours.

Start with one workflow