What I build
You probably have a rough idea of what you want. My job is to pin down what's actually worth building, then build it. Here's the work, and what you walk away with each time: working software running in your stack, owned by your team.
RAG & knowledge systems
Grounded answers over your own data, without the hallucinations that get a project shut down.
You get: An ingestion + retrieval pipeline, an eval set that measures answer quality, and a working assistant or API your team can extend.
Agents that take real action
Multi-step, tool-using agents that do work, not just chat about it.
You get: An agent wired into your APIs and tools with guardrails, retries, error-handling, and an audit trail (I've built exactly this over email, Brex, and enrichment APIs).
AI workflow automation
The unglamorous internal work that quietly saves hours every week.
You get: Automations for triage, drafting, research, and back-office flows, integrated into the tools you already use and measured in hours saved.
Production hardening / LLMOps
Turn the promising prototype into something you can actually rely on.
You get: An eval harness, cost and latency controls, observability, prompt/version management, and the fixes that get a stalled pilot to production.
Model selection & fine-tuning
The right model and the right technique, decided by testing, not vendor decks.
You get: A model and approach recommendation backed by evals on your data, plus fine-tuning or distillation where prompting genuinely isn't enough.
Governance & safety
The guardrails and supervision that let a cautious team say yes, without betting the company on a black box.
You get: Guardrails, PII handling, audit trails, and human-in-the-loop where it matters, so leadership can approve with confidence.
Not sure which of these you need?
That's the first conversation, and usually the most valuable one. Tell me what you're trying to do and I'll tell you which of these (if any) actually moves the needle for you.