Projects

What I build

Working systems in agentic analytics and LLM evaluation — not slide-ware.

Flagship · in progress

Agentic Analytics

An LLM agent that runs a real analytical workflow over public data: it plans, queries, and critiques its own output with an LLM-judge before it answers — returning a cited, verified narrative. Wiring an agent to a database is the easy part; the work is knowing when the answer is wrong.

Read the writeup →

Tooling

More soon

Additional experiments in agentic analytics and LLM evaluation will land here.