enterprise ai architecture & advisory · rochester, mn

16+ years architecting distributed cloud systems and mission-critical AI — moving generative AI from fragile prototypes to resilient, HIPAA- and HITRUST-compliant platforms on GCP, Rust, and Go.

or start a conversation →

fig. 00 · drag to orbit · rendered in zig/wasm

three things

Ship agents that hold up in production.

tool loops · evals · humans in the loop

Build on infrastructure auditors accept.

HIPAA · HITRUST · in-tenant by default

Leave a team that can run it without me.

enablement · not dependency

how the work thinks

An agent that works is an agent whose control loop you can draw on a whiteboard. The interesting parts are the state machine around the model calls, the tools you chose to expose, and the eval harness that tells you whether the last change helped.

That node riding the circuit? It is bound to your scrollbar — scroll up and it runs the loop backward. The same engine drives everything moving on this page.

A prompt chain drifts by the fifth turn; a state machine can't. Every transition is enumerated, every tool call is gated, and an auditor can read the one path the system is allowed to take — which is the actual argument for shipping agents into a regulated environment.

web app contains agentUser talks to a web app. Inside the app, an agent loop calls tools and returns.WEB APPuseragenttool · call · looptools
Deterministic GateEval HarnessState MachineTool Isolation
fig. 01 · the loop — scrubbed to your scroll

what I help with

all services →

selected work

the full index →

recent writing

all posts →