I design and build multi-agent systems with agentic memory and human-in-the-loop governance. 25+ years of enterprise architecture, CRM, and customer engagement technology. The rare combination of deep enterprise experience and hands-on AI systems building.
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.
Designed a memory system where organizational knowledge manages itself: ingesting, evaluating, connecting, consolidating, and retiring information through an automated digestive pipeline. Not passive retrieval. Active knowledge metabolism.
Built a framework coordinating a dozen specialized AI agents through a shared backlog with human-in-the-loop governance. Includes a Project Control Center with approval queues, session isolation, conflict detection, and automated review evaluation. Used daily as my primary development environment.
Applied the multi-agent framework to Salesforce development workflows with bidirectional Jira integration, Confluence documentation sync, and automated requirements traceability from business need to deployed code. Currently in UAT.
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.
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.
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.
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.
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.
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.
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.
Self-contained, interactive HTML presentations covering the architecture, the research, and the strategic vision. Each one is a complete narrative, not a slide deck.
Deep technical walk-through of the three-layer memory architecture, the digestive pipeline, and how knowledge compounds across agent sessions.
Available on request
Strategic pitch for an enterprise-wide knowledge architecture that connects organizational silos through a shared knowledge graph with curated claims.
How multi-agent orchestration transforms the software delivery lifecycle: from requirements through deployment with continuous validation.
Available on request
Comparative analysis of the agentic memory landscape: academic papers, open-source projects, and commercial products evaluated against the architecture.
Research20+ external sources pressure-tested against the architecture. Claim traceability, supporting evidence, and gaps identified. For the thorough reader.
How to synthesize signals across customer touchpoints into a unified engagement context. CRM, identity, behavior, and real-time orchestration.
Available on request
Observations from building multi-agent systems for real enterprise work. No theory. Just what I've learned.
Why a dozen fast agents without shared memory is just expensive repetition.
The distinction most teams miss, and the three-layer architecture that solves it.
Approval gates, bounded authority, session isolation, and calibrating the human-in-the-loop.
Why retrieval-augmented generation solves the search problem but not the knowledge problem.