What I do
I build AI systems that hold up on real data and real workflows: retrieval you can check, agents that finish the job, and the evaluation that tells you when either is wrong.
01 · RAG & document intelligence
Answers you can trace to the source
Retrieval over real documents (scans, tables, long filings) with citations that point at the exact page.
Proof: Atlas
02 · Agents & multi-step workflows
Agents that finish multi-step work
AI that carries a task across tools and steps, with checks between steps and a human where it matters.
Proof: Atlas pipeline · production experience
03 · AI reliability & evaluation
Know when your AI is wrong
Evals, verification gates, tracing and cost tracking, built into the system instead of bolted on.
Proof: Greenwash · Atlas evals
04 · MCP & tool integrations
Connect AI to the systems you already run
MCP servers and tool integrations with scoped permissions and audit trails.
Proof: production experience
How I approach it
- 01
Understand
The problem, the data and what a wrong answer costs, before choosing any model or framework.
- 02
Thin slice
One narrow path working end to end on real inputs, early.
- 03
Measure
Evaluate on real cases. Decide with numbers, not demos.
- 04
Harden
Failure handling, tracing, cost limits and documentation.