Enterprise AI.
Built, Not Theorized.

I design and build multi-agent AI operating systems with living memory, local inference, and human-in-the-loop governance. 25+ years of enterprise architecture — now building the agentic infrastructure that compounds knowledge across sessions, agents, and machines. The rare combination of deep enterprise experience and hands-on AI systems building.

Different domains. Same architecture spine.

Most organizations experimenting with AI agents are running single-agent demos against isolated problems. I design and build systems where multiple specialized agents collaborate under structured governance, building on each other's work through shared memory. I also ship practical AI-powered tools that real teams use every day.

Living Memory & Knowledge System

Designed a memory architecture where organizational knowledge manages itself: agents file knowledge chunks as they learn, auto-promoted lessons compile into a living wiki, and stale claims decay. Not passive retrieval — active knowledge metabolism that compounds across every session. Inspired by Karpathy's "Software 2.0" and Cherny's context engineering.

knowledge graphs digestive pipeline living wiki agent reflections auto-promotion gates decay + consolidation

autogenous-synthesis Forge

The development OS behind every project here. Forge is a harness engineering framework — it doesn't add AI to an existing process, it replaces the process entirely. Twelve specialized agents (architect, builder, analyst, reviewer, tester, debugger, and more) operate under structured SOPs, a governed backlog, TDD enforcement, and persistent session memory. The loop: a planning agent decomposes work into tickets via the PDT API; Stewart grooms intake to ready with verified AC and an agent assignment; the dashboard auto-generates an agent-scoped prompt at the ready→in-progress transition; one click on Launch copies it to the clipboard, the agent runs in a fresh session, and submission triggers an automated multi-stage review gate (lint, 700+ test suites, Eval, code review, pre-commit) that auto-closes the ticket on pass or stages a "fix it" prompt via a Relaunch button on fail. When something fails, the fix is never "try harder" — it's "what capability is missing, and how do we make it legible to the agent?"

harness engineering TypeScript / Node.js SQLite 12 specialized agents approval gates TDD enforcement session memory agent SOPs
Documentation →

Enterprise Workflow Automation

Applied the Forge framework to Salesforce development workflows with bidirectional Jira integration, Confluence documentation sync, and automated requirements traceability from business need to deployed code.

Salesforce (Apex / MCP) confidence evaluation brownfield discovery human-agent co-development Jira integration test coverage

HR Media Campaign Platform

Designed and built an internal media campaign management system used by the HR People Team. Multi-format content creation (AI-generated audio, avatar video, text), Slack distribution, branded media player with engagement analytics. In active daily use.

Node.js / Express PostgreSQL Google TTS / HeyGen Slack integration SSO

niKi: Now I Know It

A product bet exploring AI-powered compounding learning. Students upload course notes (images, PDFs, docs) and an LLM extracts atomic concepts with prerequisites and cross-course connections into a personal knowledge graph. Builds scoped study guides, with 8 built-in skills (concept extraction, confusion pair detection, exam postmortem, bridge detection). The same knowledge-graph-plus-learning-layer pattern from the enterprise work, applied to student learning.

Node.js LLM vision API knowledge graphs prompt templates portable / self-contained

Customer Contextualization Framework

Designed a framework for synthesizing customer engagement signals across touchpoints into a unified context layer. Identity resolution, CRM architecture, behavioral data, and real-time orchestration powering personalization and support cost reduction.

identity resolution rules engine relevance scoring Builder.io AWS Redshift Salesforce CRM

Strata: AI Job Search OS

An autonomous AI operating system where eight specialized agents collaborate through governed PostgreSQL to discover, evaluate, match, and help apply to jobs. Three-layer dedup eliminates 95% of noise before LLM scoring. Two public PyPI libraries (strata-match, strata-harvest). Budget: $10–36/month for full operation.

FastAPI / PostgreSQL pgvector 8 governed agents ARQ + Redis 3-layer dedup open source (PyPI)
Documentation →

Local AI Infrastructure

A Mac Mini cluster running schedule-driven local inference across three machines. Gemma 4 31B (near-lossless q8 quantization) handles deep scoring overnight; Qwen3 30B MoE (60–70 tok/s) runs during dev hours — automatic launchd transitions between them. LiteLLM routes Strata's pipeline stages to the right model: fast and balanced stages to Qwen3, deep-score stages to Gemma 4. nomic-embed-text provides always-on 768-dim embeddings. GLM-OCR handles resume parsing. Shadow-mode calibration benchmarks local quality against cloud models continuously. Zero variable inference cost for production workloads.

Ollama / LiteLLM Gemma 4 31B (q8) Qwen3 30B MoE nomic-embed-text GLM-OCR launchd scheduling Tailscale VPN shadow-mode eval

Memory is the multiplier. Agency is the force.

Without memory, agency does the same work repeatedly. An agent fleet without shared memory is individually capable but collectively starts over every time. The architecture I designed solves this with three distinct layers, each with its own failure modes and quality signals.

The learning layer is the part most teams skip. It's where raw experience becomes structured understanding: what worked, what didn't, what should be applied next time. Without it, you have storage and retrieval but no compounding.

Retrieval
Right knowledge, right agent, right moment
Personalization
Learning
Reduce, reflect, consolidate
Most skip this
Storage
Where knowledge lives
Infrastructure
The difference between agents with a vector database and agents with a memory system that compounds is the difference between a tool and a team.

Governance as Architecture

Speed without governance means fast in the wrong direction. The framework enforces bounded authority (each agent has a narrow, architecturally enforced scope), continuous approval gates, automatic audit trails, and session isolation with conflict detection. Governance isn't a policy layer. It's a first-class architectural concern.

Enterprise Reality

The system is designed for real enterprise infrastructure: Salesforce with governor limits, Jira with all its workflow complexity, Confluence as a living documentation target. Most agent demonstrations run in isolation. This one operates where the constraints are real and the consequences matter.

Standing on strong shoulders. Taking it further.

Inspirations & Synthesis

This architecture didn't emerge in isolation. It synthesizes ideas from Andrej Karpathy (Software 2.0, LLM OS), Boris Cherny (context engineering as the core discipline), Program-Aided Language Models (PAL) (structured reasoning through code), and Demis Hassabis (systems that learn from experience, not just data). The key insight: most agentic systems bolt memory onto agents as an afterthought. We built memory as the foundation and agents as the consumers.

Where We're Different

Memory platforms like Mem0, Zep, and LangMem solve recall. Orchestration frameworks like CrewAI and LangGraph solve coordination. Neither solves compounding — the ability for a fleet of agents to get measurably better over time. Our system does: knowledge chunks auto-promote through confidence gates into a living wiki. Stale claims decay. Agents start sessions by reading what the fleet has learned, not by re-researching. The learning layer is the differentiator.

25 years of building systems
that make organizations smarter

The thread through my career: designing technology systems that help organizations understand their customers, make better decisions, and operate more intelligently. The actors have changed over 25 years. The architecture thinking hasn't.

2025 – 2026
Agentic AI & Multi-Agent Systems
Head of GTM Engineering
Designed and built a multi-agent orchestration framework with living memory, human-in-the-loop governance, and enterprise workflow automation (3x Salesforce dev acceleration). Built Strata — an autonomous AI job search OS with 8 governed agents, 3-layer dedup, and local Gemma/OCR inference across a Mac Mini cluster. Shipped an AI media campaign platform for HR. Published two open-source PyPI libraries.
2013 – 2025
Customer Engagement & GTM Platform
Executive Director, Customer Engagement Solutions
Architected customer data platforms, identity resolution, CRM strategy, and marketing technology for a major EdTech publisher. Converged 10 product companies onto a single Salesforce instance. Built a fully integrated customer engagement ecosystem with compounding flywheels and feedback loops, providing decision support to sales and execs, and accelerating a $250M pipeline.
2002 – 2013
Global CRM & Sales Technology
Executive Director, Major Financial Institution
Nearly 9 years as global CRM product owner for 5,000 users, then Fixed Income IT portfolio lead managing a $20M technology budget. Built consolidated sales reporting, analysis, and coverage platforms replacing legacy systems.
1996 – 2002
Digital Product & Platform Engineering
VP Product Management / Sr. Technical PM
Built digital platforms for performing arts organizations and Fortune 500 companies. Designed e-commerce and ticketing integrations that transformed how Broadway theaters sold tickets online.

Technical presentations and deep-dives

Self-contained, interactive HTML presentations covering the architecture, the research, and the strategic vision. Each one is a complete narrative, not a slide deck.

Lessons from building

Observations from building multi-agent systems for real enterprise work. No theory. Just what I've learned.

Let's talk.

I'm looking for my next role leading AI-native engineering organizations — where the ability to actually build agentic systems, architect for enterprise reality, and ship production-grade AI infrastructure all matter. VP/Head of AI Engineering, AI Strategy, or Agentic Platform leadership.