AI Solutions Engineering & Technical Sales | Enterprise Discovery to Deployment | Advisory & Governance | Business Value First

Understand the workflow.
Then build the AI.

I build enterprise AI for decisions where money, risk, and accountability matter—connecting financial-services experience with AI architecture, infrastructure economics, and controlled execution.

Based in Austin. Open to in-office or hybrid opportunities within Texas and meaningful business travel.

FEATURED / FROM WORKFLOW TO DELIVERY

Eight projects. One delivery discipline.

Secret and agent-authority scanning, security investigations, customer onboarding, commercial research, cloud authority, governed data, infrastructure economics and conversational knowledge.

FirstSync is a hosted reference implementation with synthetic orgs and precomputed model proposals. Inspect each repository for its validation evidence and operating scope.

FEATURED / DEADBOLT · GITHUB MARKETPLACE

Find leaked keys.
Review agent authority.

Catch credential exposure and risky agent configurations before commit or build.

A leaked key is only
part of the problem.

DeadBolt checks local files, staged changes, git history and container layers for leaked credentials and risky MCP or agent settings. Deterministic rules estimate potential authority and help a human prioritize what to review.

The offline core requires no API key or AI model. Run it from a Mac or Linux terminal, use the pre-commit hook, or add the published GitHub Action to a workflow.

Proposals, with people in control.

Text, JSON and SARIF reports connect findings to content-hashed remediation proposals. DeadBolt records human decisions in a hash-chained ledger and never uses discovered credentials or executes a fix.

Published v0.1.0 release and Marketplace Action. The synthetic demo produces 30 findings. Sixty automated tests and Linux CI across Python 3.10–3.13 cover detection, redaction, staged scans and approval integrity.

Authority is estimated; effective access remains unknown. Detection has finite rule coverage. Approver names are operator labels, and detecting a completely rewritten ledger requires a separately trusted head. The local AI model is optional; real-model inference remains unverified.

THE CONNECTION / PEOPLE, PATTERNS & SECURITY

Penumbra closes a loop.

Agents that help defend an organization must themselves be defensible.

No single signal tells the whole story.
The pattern matters.

Penumbra takes its name from the partial shadow: the space between full light and darkness. My fascination with Kepler led me, at Harvard, to write about the music of the spheres. What I carry into security architecture is the importance of looking at the whole system.

The moon has two sides, and so do I: the extrovert who works across executives, engineers, Legal and HR, and the focused builder who turns those conversations into working systems. Penumbra needed both.

In 2017, I was writing Hacking The Human about insider threats, social engineering and cybercrime-as-a-service. Today I build agentic AI. Penumbra connects those threads through evidence-linked investigation, explicit tool boundaries and human-reviewed containment.

Synthetic reference implementation with a keyless deterministic demo and optional Claude backend. Live telemetry connectors and SSO-bound approval remain roadmap work; containment is simulated.

FEATURED / SIGNALDESK · OPENAI + SALESFORCE

Evidence before outreach.

Company research becomes a reviewable decision—not automatic permission to act.

Research the opportunity.
Earn the right to act.

SignalDesk connects OpenAI-powered company discovery, source-linked candidates and a human review queue. Exact-draft approvals, persistent Do Not Contact suppression and explicit research limits keep the workflow bounded.

The Salesforce GET-only preview adds a separate, read-only enterprise integration boundary. The XERJ team selected that implementation for its public code-reference corpus.

A system that knows when to stop.

In the documented workflow, a person approved an acquisition handoff. Separately triggered research could not verify the contact, so SignalDesk retained Needs evidence instead of producing an approvable message.

In the developer-org Salesforce run, two synthetic Leads produced one blocked and one requiring review. Lead permission metadata reported query access allowed and create/update/delete denied. The preview made no CRM writes and granted no outreach authority.

Local, single-user reference application. Live observations are developer-operated; automated provider tests are mocked. Delivery is simulated. No production deployment or customer ROI is claimed; corpus selection is not certification.

BUSINESS VALUE / ENGINEERING EVIDENCE

Three areas of impact.

Strategy, governance, and execution—each connected to working code and reviewable evidence.

ENGINEERING DISCIPLINE / MODEL-AGNOSTIC ARCHITECTURE

Choose the capability. Govern the execution.

Model selection is an engineering decision—not a brand preference. Accuracy, latency, cost, context, retrieval, security, and failure behavior determine the fit.

MULTI-MODEL EVALUATION · CONTROLLED RUNTIMES

The model is a component.
The architecture is the product.

My work spans agentic workflows, model-assisted engineering, enterprise integrations, and deterministic control layers. I evaluate multiple model ecosystems for specific workloads while keeping policy enforcement, permissions, validation, and human accountability outside the model.

01 / OPENAI

GPT / Codex

Structured research & software engineering

Bounded AI research, source-linked findings, coding assistance, and validated data workflows.

Inspect a bounded OpenAI workflow
02 / ANTHROPIC

Claude

Complex reasoning & tool-use design

FirstSync uses Claude for schema mapping. Penumbra offers a Claude tool-use backend behind the same scoped tools and policy gate as its deterministic demo.

Inspect FirstSync and its evaluations
01Route deliberatelyQuality · latency · context · cost
02Bound the toolsRead-only where possible · explicit grants
03Validate independentlySchema · policy · evidence · failure
04Keep humans accountableApproval · audit · uncertainty

Implementation boundary: The portfolio demonstrates governed agent workflows and bounded integrations. OpenAI and Claude implementations are shown separately; a unified production router is not claimed. Multi-agent orchestration and multi-model routing are distinct capabilities; provider-specific production claims require corresponding code and operational evidence.

THE EXECUTIVE LENS

Architecture changes the quality of decisions.

“The model may propose. The system determines what is authorized.”

I design for the business consequence—not just the successful model response.

$1.2M+Annual cloud savings in prior consulting work
70%Reduction in manual reporting in prior work
10K+Daily users supported by prior platforms

Prior career outcomes; not measured returns from these reference implementations.

BREADTH / SUPPORTING EVIDENCE

Follow the decision into the engineering.

Explore the wider portfolio across agent authority, capital markets, supply chain, data engineering, cloud economics and cybersecurity assurance.

Open-source recognition: a bounded SignalDesk Salesforce implementation was selected by the XERJ team for inclusion in a public reference corpus. Corpus selection is not certification or a claim of measured adoption.

LET'S DISCUSS THE BUSINESS PROBLEM

Build the technology. Understand the economics. Earn the trust.

AI Solutions Engineering & Technical Sales | Enterprise Discovery to Deployment | Advisory & Governance | Business Value First. Based in Austin. Open to in-office or hybrid opportunities within Texas and meaningful business travel.

Start a conversation