AI & Automation · GTM Systems Engineering

I build production AI
that ships.

AI & Automation lead at Atlas HXM. I design, build, and harden the systems that let 50+ people run a global GTM org on AI — and I ship the frameworks that let others do the same.

Chicago, IL n8n · Azure OpenAI · Claude SDK ROSTR Framework Author AWS Certified ×2

ROSTR in action — multi-agent architecture for production AI. Explore the full framework →

The ROSTR Framework

A unified architecture for production-grade multi-agent systems — published, cited, and running in production. Four components, a five-phase taxonomy, and a persistent knowledge architecture that powers agent systems at scale.

📄 DOI: 10.5281/zenodo.19550414 ↗
Component 01

PAL

Prompt Abstraction Layer

The Intent Compiler that transforms loose natural language into strict agent runtime manifests. Five-stage pipeline: intent extraction → context injection → semantic enhancement → runtime compilation → output routing. Takes "improve the outreach workflow" and produces a fully-parameterized agent manifest with model, temperature, tool permissions, memory mode, and completion criteria. No more raw prompts — every agent invocation flows through compiled manifests.

Component 02

RAG DAL

Dynamic Acquisition Layer

Autonomous multi-pass retrieval with source credibility stratification. Three-tier architecture: Tier 1 (academic/authoritative, credibility 1.0), Tier 2 (editorial/verified, 0.75), Tier 3 (community/UGC, 0.40). Multi-pass algorithm: broad sweep → gap fill → deep verification. Confidence scoring formula weights source count, consistency, tier distribution, and recency. Knowledge is ingested, embedded, and compounded across sessions.

Component 03

NPAO

Navigate, Prioritize, Allocate, Orchestrate

A 5D phase taxonomy classifies every task: PreD (research), Design (architecture), Development (build), Deployment (ship), Debugging (fix). Four-dimensional priority scoring weights phase urgency, dependency impact, business impact, and resource efficiency. Agent allocation uses vector similarity + specialization overlap + load scoring. Orchestration patterns: sequential chains, parallel fan-outs, aggregation fan-ins, conditional branches.

Component 04

Rostr Hub

Agent Operating System

Persistent reference architecture with four-level state management: session (ephemeral), project (persistent — decisions, artifacts, learnings), organization (evolving — identity, ICP, positioning), agent (portable — skills, preferences, calibration). Knowledge compounds across sessions. The Hub provides scoped namespaces, hierarchical credibility, and cross-namespace permission gates. Agents don't restart from scratch — they load context from the Hub.

5D Phase Taxonomy — Every task knows where it belongs

P0
PreD
Determine IF to build. Problem definition, competitive research, go/no-go.
P1
Design
Define WHAT to build. Architecture, data models, API contracts, tech choices.
P2
Development
Build it. Implementation, testing, code review, documentation.
P3
Deployment
Ship it safely. Staging QA, canary deploys, monitoring, rollback procedures.
P4
Debugging
Fix what's broken. Root cause analysis (not symptom), fix, regression testing, post-mortem.
🏢

Gency AI — SOP to Agent Pipeline

The ROSTR framework powers the CoE project intake system — cutting idea-to-scoped-project from 4–8 hours to under 30 minutes. Every GTM automation project routes through PAL compilation and NPAO phase classification.

🤖

Gency AI

The agency's core product: SOP → intelligent agent. JTBD Analysis maps intent, PAL/NLP extracts and compiles it, the ROSTR system builds the agent. Every client engagement runs on this pipeline.

📚

Published & Citable

Full academic paper on Zenodo with DOI. Formalized architecture with algorithms, formulas, and implementation templates. Not a blog post — peer-reviewable, citable research. Read the paper ↗

8+
production GTM automations live
~242
deals auto-screened, every one auditable
0→stable
post-sales workflow recovered from 84% failure
<30m
idea → scoped project, down from 4–8 hrs
30+
Claude skills & agents for GTM team
$5M+
consulting pipeline attributed

What I work with

Production-grade tools across AI, orchestration, GTM, and cloud.

AI / LLM

Azure OpenAI (GPT-4o / GPT-5) Claude + Agent SDK Claude Skills OpenAI Assistants API Google Gemini AWS Bedrock Prompt Engineering RAG & Grounding

Orchestration & Automation

n8n Make.com Zapier MCP Webhooks Custom JS Engines REST APIs Vercel Cron

GTM & CRM Stack

HubSpot API Clay Salesforce Amplemarket ZoomInfo Avoma Factors.ai Apollo.io

Cloud & Infra

AWS (EC2, S3, Lambda) Azure Blob Storage Vercel Supabase Docker GitHub Actions Microsoft 365

Languages & Frameworks

JavaScript / TypeScript Python React Node.js Next.js HTML / CSS SQL Tailwind CSS

Design & Productivity

Asana Notion Airtable Figma Excel / Sheets Mailchimp Slack

Enterprise Production

Production AI systems shipping inside a 50+ person GTM org at Atlas HXM.

Agent Skills Library

30+ reusable Claude skills and agents for the GTM team — prospecting, workflow ops, revenue enablement, content at scale.

clay-prospecting-engine
Build and execute Clay prospecting tables with enrichment logic
n8n-engineer
Build, debug, and deploy n8n production workflows
gtm-architect
Design GTM systems and automation architecture end-to-end
new-project-system
Intake engine: raw input → full project package (PRD, architecture, plan)
case-study-builder
Build data-rich case studies from project records and metrics
hubspot-data-analyst
Analyze CRM data, pipelines, and revenue in HubSpot
saas-architect
Full SaaS platform architecture design and scaffolding
atlas-proposal-builder
Build Atlas proposals and decks from deal context
workflow-builder
General-purpose workflow construction and automation
dashboard-builder
Build dashboards and reporting interfaces
rostr-builder
ROSTR framework implementation and orchestration
atlas-agent-factory
Build new Atlas agents from natural language descriptions

30+ skills total. Full catalog in master knowledge base.

Product Library

Products and platforms I've founded, built, and shipped — from AI consulting to civic infrastructure.

🤖

GPTPAT

Production AI for SMB and mid-market: chatbots, email automation, ed-tech, Shopify workflows.

gptpat.co →
🏛️

Your48

Civic intelligence platform for Chicago's 48th Ward — precinct directory, business database, intake forms, ward dashboard.

your48.vercel.app →
📊

RevEnabled

GTM systems consulting. Dark Roast Media ($1M→$3M ARR), Rand McNally ($5M pipeline, 2,000% engagement lift).

revenabled.com →
📚

ROSTR Framework

Published multi-agent architecture: PAL + RAG DAL + NPAO + Rostr Hub. 5D phase taxonomy. Zenodo DOI.

Zenodo DOI →
🎵

Artist EPKs

Electronic Press Kit platform for independent artists. Dark theme, gold accent. Next.js 16 + Supabase + Stripe.

artistsepks.vercel.app →
🔬

Scalytics.io

GTM systems for private-AI / federated-data startup. ICP, outbound tooling, CRM automations with PhDs.

scalytics.io →
🤖

Gency AI

Agent development & adoption agency. SOP → intelligent agent via ROSTR. AI teams, n8n/Make, IDE setup, custom MCPs.

gencyai.vercel.app →
PD

About me

I'm a production AI systems builder based in Chicago. I lead AI & Automation for a global Employer-of-Record platform, where I've shipped 8+ production automations that screen deals, prepare reps, automate follow-ups, and govern spend — all built on a hybrid architecture where LLMs handle the messy text and deterministic code makes every decision auditable.

Before AI, I spent years in enterprise sales at Uber and Upwork, which is why I build differently: every system I ship is designed for the operators who will actually use it. I also serve as a precinct captain for Chicago's 48th Ward, where I built a civic intelligence platform connecting residents to their government.


Currently
GTM AI & Automation Manager at Atlas HXM
Location
Chicago, IL · Open to relocation
Certifications
AWS Certified AI Practitioner + Cloud Practitioner
Full bio →

Full resume

Complete FDE / GTM / AI Engineer resume with experience, civic leadership, publications, and impact metrics.

View Full Resume