I build governed AI tools for leading customers.
Fifteen years shipping production AI in regulated, data-sensitive industries — healthcare, life sciences, and financial services. I take agents and ML systems from prototype to audit-ready, with the evals, guardrails, and SOC2/HIPAA evidence that let Legal, Security, and Compliance all say yes.
What I do
Regulated industries don't need more demos. They need AI that ships — agents and pipelines that are measured, bounded, and audit-ready, built end to end from architecture through production.
AI agents in production
Agentic systems with tool-routing, hybrid retrieval (RAG), and guarded text-to-SQL — deployed where work already happens: Microsoft Teams, Copilot Studio, and zero-trust corporate networks, with managed-identity auth throughout.
Evaluation, safety & guardrails
AI output gets measured and bounded, not trusted blindly. Deterministic eval harnesses, type-safe agent loops, and objective gates that run before any human approval — a thick boundary around a creative interior.
Data pipelines & analytics
Fragmented operational data unified into a single source of truth — LLM classification against domain rules, probability-weighted forecasting, idempotent re-runs, and strict separation of sensitive identifiers from shared reporting.
Compliance & governance
SOC 2 Type II run end to end — gap analysis, control-policy authoring, evidence, audit readiness — plus HIPAA-aware architecture, PHI-safe data lanes, and security boundaries reviewed with zero high/critical findings.
AI Readiness & Risk Assessment
A clear-eyed read on where your organization actually is — the controls in place, the gaps that block deployment, and a sequenced path to a governed pilot.
Selected work
Recent engagements building AI agents, evaluation systems, and data pipelines for regulated, data-sensitive organizations.
Client and proprietary product names omitted · technologies and architecture described in full · most delivered solo or in small teams, end to end.
Clinical site-discovery agent
A natural-language agent for clinical-trial site feasibility over hundreds of thousands of documents — tool-routing across hybrid (vector + keyword) search, a guarded read-only text-to-SQL pipeline, and peer-adjusted feasibility scoring. OCR fallback lifts effective corpus coverage to ~99.9%; a JWT/JWKS-hardened bot ingress passed security review with zero high/critical findings.
Enterprise knowledge agents
Two production agents deployed inside a zero-trust corporate network — a project-discovery agent mining tens of thousands of engineering work items, and a product-knowledge agent over hundreds of mixed-format documents — surfaced through a Copilot Studio chatbot, with managed-identity auth throughout and a search-quality evaluation harness.
Clinical evidence platform
A multi-service platform letting clinicians query real-world data and literature with LLM synthesis — React/TypeScript front ends, a SMART-on-FHIR OAuth flow into EHR systems, a graph-based Python search service, and an MCP tool-server exposing platform capabilities to third-party LLM clients with PHI-safe handling.
Evidence-discovery proof of concept
An end-to-end conversational screening prototype over public trial registries and biomedical literature — tiered cross-source matching, semantic retrieval with a three-state eligibility model (match / no match / not specified), composite-score ranking, and a conversational UI with a live audit diagram and full provenance.
Runs an AI coding agent in isolated git worktrees and gates output against objective checks — correctness, latency budgets, extraction F1, schema and migration safety — before any human approval.
Static typing and boundary validation that catch AI-generated errors at the edge, with a strict split between the production runtime and the offline eval.
A gated build-vs-adopt evaluation of a vendor SDK against a battery of auth and channel tests that shaped a downstream production decision.
A weekly pipeline unifying fragmented operational systems into one source of truth — LLM classification against domain rules, probability-weighted expected value, and prioritized, owner-assigned action queues.
Cash-flow reconciliation across accounts with trend-based runway forecasting, plus a set of operational automation and cost-ledger tools with strict data-separation rules.
Ran a SOC 2 Type II engagement end to end — gap analysis against the trust-services criteria, authoring and rationalizing the control-policy set, organizing audit evidence, and driving audit readiness with a quantified risk-budget model and adversarial review cycles.
How I work
Security from the start
Least-privilege access and explicit trust boundaries are designed in, not bolted on.
AI made evaluable
Deterministic gates and honest measurement — output is judged, never trusted blindly.
Sensitive data, separated
Protected identifiers stay isolated from anything shared or reported on.
Shipped, with a clean handoff
Tests, infrastructure-as-code, and documentation come with the delivery.
Writing & thinking
A physicist's framework for changing your life — feel the local slope, take one small step downhill, and repeat. Why the modest algorithm usually beats the wholesale transformation, and the rare moment it doesn't.
Read essay →The unglamorous habits — real evals, tests, contracts at the seams — that keep AI-assisted building from collapsing into throwaway spaghetti. Eight rules I actually use.
DeepSeek at $0.14 a million tokens and $160 for an hour of a frontier model are two points on the same curve — not an argument about whether AI is cheap.
The longest task an agent completes reliably — and why the curve is steeper than your roadmap assumes.
The economics, the opportunity cost, and the unstructured time that paid off more than the degree.
Experience
Governed Teams agents on Azure; evals, guardrails, and SOC2 evidence packs; Fabric/FHIR pipelines.
Established MLOps and AI governance across a 19,000-person clinical research organization.
Built the US lab from the ground up and scaled US IT.
Real-time inference from 200+ cancer centers; CI/CD and model deployment in an FDA-regulated environment.
Cloud platform and discharge-forecasting models from inception — 85% accuracy in clinical use.
- Azure Data Scientist Associate (DP-100)
- Azure AI Engineer (AI-900)
- Azure Fundamentals (AZ-900)
- AWS Solutions Architect — Professional
Get in touch
Governance you can actually ship.
The best first step is a short scoping call. Bring a workflow you'd like to make governed and audit-ready, and we'll talk through what's involved.
Book a 20-min call →