Forward-deployed AI · Enterprise systems

From ambiguous problems to governed AI in the real world.

I design and ship agent systems end to end—from workflow discovery and evidence architecture through evaluation, identity, cloud deployment, and operations.

Sole creator
A statewide political-intelligence system spanning evidence, geography, agents, and campaign products.
AWS + Azure
Delivery experience across serverless, containers, data platforms, and enterprise identity.
Active TS/SCI
National-security experience with a bias toward explicit authorization and evidence boundaries.
15 years
Across intelligence, enterprise architecture, technical delivery, and AI product building.
Selected systems

The hard part is rarely the model.

These systems begin with fragmented evidence, hidden workflow rules, regulated users, or an unfamiliar operating environment—and end as software people can interrogate, evaluate, and run.

01

Rhode Island Political Intelligence System

A statewide campaign research and strategy workspace connecting public records, elections, geospatial voter-roll intelligence, candidate dossiers, money, public decisions, and an evidence-native agent.

Product insight: a complex strategic answer becomes useful when the map, source record, identity state, counterevidence, and reasoning boundary remain inspectable.
Open the flagship case study
02

Governed intelligence platforms

A production federal opportunity-intelligence system evolved into a durable enterprise agent architecture with contracted tools, corrective retrieval, evaluation, and authorization built into the runtime.

Architectural insight: agents become dependable when tools carry evidence, limits, and authorization—not when prompts merely ask models to be careful.
Read the case study
03

State-government delivery fleet

A repeatable pipeline turns solicitations into working demonstrations, technical packages, and deployment-ready software across corrections, public services, justice, and assessment workflows.

Delivery insight: a working system changes a proposal conversation from “can you build this?” to “how do we put this into the bid?”
See the delivery system
04

Theoria

A public, source-aware Orthodox study product built on a retrieval engine, domain-profiled corpus, conversational application, durable threads, and protected edge/origin deployment.

Retrieval insight: the corpus, source posture, tool shape, and evaluation set matter as much as the model answering the question.
Explore Theoria
05

Product platforms

Serverless products for contractors and professionals: customer provisioning, identity, billing, structured AI document workflows, hosted sites, and usable business software.

Product insight: automation only creates value when the customer journey—from event to provisioned experience—is coherent.
View the product work
How I work

Stay with the problem until the system is operating.

Forward deployment is a continuous loop between domain experts, evidence, product decisions, software, and the constraints of the target environment.

01 / Discover

Find the real workflow

Interview users, inspect artifacts, and surface the tacit rules that do not appear in the request.

02 / Contract

Establish the evidence boundary

Define sources, identity, authority, freshness, claim limits, and the tools the agent is allowed to use.

03 / Prove

Build and evaluate

Ship the smallest real workflow, observe failures, add regression and adversarial tests, then widen deliberately.

04 / Operate

Deploy and transfer

Package the runtime, identity, observability, runbooks, and decision history so another team can own it.

Enterprise credibility

Technical judgment shaped by operations.

My path runs from Army intelligence through enterprise transformation and aerospace systems to governed AI delivery. The thread is translating consequential work into systems people can act on.

Booz Allen Hamilton

Enterprise architecture, technical program leadership, and national-security software delivery.

CVS Health

Technology modernization, requirements, and business-to-engineering translation.

SpaceX

Enterprise systems analysis and implementation support in a high-velocity engineering environment.

U.S. Army

All-source intelligence, operational planning, and decision support with the 82nd Airborne Division.

Ask about the work

A portfolio you can question.

The assistant retrieves from a versioned set of approved public claims, routes the question, shows the evidence it selected, preserves caveats, and links each answer back to the work.

Portfolio assistant

Ask About Arthur

Question routeWaiting for a question Evidence selected0 approved claims CorpusPublic portfolio
Visible activity traceExecution stages only—not private reasoning
  1. Route questionWaiting for a question.
  2. Retrieve public evidenceApproved records only.
  3. Compose bounded answerSelected claims constrain the response.
  4. Validate citationsEvidence and caveats remain visible.
Ask about Arthur's experience, projects, architecture, or delivery decisions. Every answer shows the approved public evidence selected for that turn.