About

Building the agentic platform enterprise learning deserves.

I'm Garth Puckerin — an AI / Agentic Systems Engineer building agentic AI for the enterprise domain I know from the inside. I design and ship multi-service platforms: a Neo4j knowledge-graph memory engine running in production as the context layer for my coding agents; an LLM-orchestrated content and coaching engine; and an event-driven integration layer built to solve a real credit-union integration problem.

Underneath the AI work sits 18 years administering and integrating enterprise learning and workforce platforms — Docebo, Workday, SumTotal, and SAP SuccessFactors — across banks, pharma, and hospitals, plus a self-taught database habit going back to 1992 (FoxPro to Access to SQL/PostgreSQL to Neo4j) and a grants database I built for the grants management office at NYU's School of Education in 1998. That domain depth is the moat: I know exactly where enterprise learning systems break, and I build systems that account for it before they ship.

The platform is real and I keep its status honest. The memory engine is in production, self-hosted on a Synology DS1821+, giving my agents cross-repo memory and cutting token spend by serving only the components a task needs. The content engine and the integration layer are release candidates; the integration layer was built to solve the exact UKG, Axonify, LinkedIn Learning, and Docebo integration seams I hit on the job, though it was never deployed there. The requirements pipeline — unstructured input to versioned requirements — is deployed and in active hardening. Their names drop one at a time, every Thursday through October 1, on the reveal wall.

My edge is the domain depth most AI engineers lack: I know what GxP and banking compliance require of software, and how to land working systems with real stakeholders from requirements through UAT to production. I develop daily with AI assistance — Claude Code, Cursor, Windsurf — and still take on LMS administration, learning-technology, and integration contract work, where those two skill sets reinforce each other rather than compete.

Core Competencies
Agentic AI & LLM Orchestration Knowledge Graphs (Neo4j) Enterprise Integration & Orchestration AI-Assisted Development Requirements → UAT → Production LMS Administration & Integration Compliance & Data Governance (GxP, banking) Self-Hosted Infrastructure
Agentic Platform
A self-hosted stack of AI services — memory, content generation, requirements capture. One in production, the rest nearing release; names reveal Thursdays through Oct 1.
Enterprise Integration
An event-driven integration layer (FastAPI · NATS · Temporal) built to solve a real credit-union integration problem across UKG, Axonify, and Docebo. Release candidate — name reveals Sep 17.
Knowledge-Graph Memory
A Neo4j knowledge-graph memory engine in production, giving coding agents cross-repo context on demand and cutting token spend through component-level retrieval — the season's crescendo reveal, Oct 1.
Regulated-Environment Delivery
GxP and banking compliance, plus requirements-through-production discipline — landing working systems with real stakeholders from UAT to production across finance, pharma, and healthcare.
AI / Agentic
Backend & Infra
LMS Platforms
Integrations & Standards