Product Architect · AI Systems Builder

JDP

I design and build AI-powered operational systems that turn complex workflows into structured, testable, reusable processes.

AI SystemsProduct ArchitectureAgent WorkflowsOperational Tooling

View Selected Systems View Case Studies

scroll

Selected Systems

Production AI systems — from agent infrastructure to operational platforms.

zoom

Execution System ▼ open

Dark Factory

Spec-first multi-agent orchestration for turning prompts into reviewable engineering artifacts.

Multi-agentSpec-firstCLI + UI

zoom

Agent Governance

AEO Kit + AEO Console

Schema, CLI, and console tooling for governing agent-facing interfaces.

SchemaCLILocal-first

zoom

Platform Prototype

NexusAI Platform

High-fidelity AI operations console prototype with local-first data and orchestration UI.

PrototypeOperator UXsql.js

zoom

Localization Engine

Omniglot

Localization systems for structured translation workflows, file ingestion, QA, TM, and glossary support.

LocalizationSpec-drivenETL

zoom

Local MLOps

AItunes

Local fine-tuning operations UI for datasets, training jobs, metrics, and adapters.

FastAPISvelteKitLocal

zoom

Knowledge OS

Knowledge Engine

Technical writer copilot and knowledge workflow system built around doc import, KB emulation, and validation patterns.

CopilotEmulatorValidation

Case Studies

Architecture, decisions, and outcomes — per system.

Execution System Case Study

Dark Factory

Explore how this system was designed, built, and validated.

// problem

Product and engineering work often starts from fuzzy intent and becomes fragmented across chats, docs, and task tools.

// what I built

A SvelteKit web app plus CLI that runs staged agent-style workflows to generate specs, architecture notes, QA plans, and task artifacts, with dry mode and local LLM provider support.

// why it matters

Shows how AI-assisted work can become repeatable, reviewable, and operational instead of disposable chat output.

// key capabilities

→Staged runs and templates
→Dry mode and local LLM backends
→Artifact-oriented outputs
→Run comparison and review flows
→CLI alongside operator UI

// primary visual

zoom

// demo flow

01 Open

Start the app and create a run from a named template (dry mode for a predictable demo).

02 Run

Walk stages so the audience sees progression without production keys.

03 Artifacts

Open a generated spec or plan-style artifact and point to structure reviewers can use.

04 Quality

Show quality or revise concepts at a high level (exact controls—needs confirmation on branch).

05 CLI

Optionally mirror the same story from the CLI for automation-minded viewers.

// screenshot gallery

Visual Proof

Interfaces from deployed systems.

Execution System Workflow orchestration — state graph view

Agent Governance Agent spec editor + eval panel

Platform Prototype Platform cost analytics dashboard

Localization Engine Review queue — multilingual diff view

Local MLOps Fine-tune experiment comparison view

Knowledge OS Retrieval trace inspector

Cross-Project Patterns

Recurring architectural principles.

◆

Spec-First Development

Specs and plans drive work: Dark Factory runs, AEO interface artifacts, and Omniglot Next Gen’s authoritative specs tree.

Dark FactoryAEO Kit + AEO ConsoleOmniglot

◆

Model-Agnostic Architecture

Dry runs, local LLMs, and swappable provider options where implemented—without hard-binding the whole stack to one vendor.

Dark FactoryNexusAI PlatformAItunes

◆

Local-First + Cloud Hybrid

Workstations and SQLite-first paths, with optional cloud sync or hosting where the repo actually wires it (console, prototype, tuning UI).

AEO Kit + AEO ConsoleNexusAI PlatformAItunes

◆

Human-in-the-Loop Validation

Review-oriented flows: Knowledge Engine validation materials, Omniglot QA in context, SME-style checks—scope needs confirmation per build.

OmniglotKnowledge Engine

◆

Deterministic Workflows

Dry mode, CLI checks, and artifact-oriented pipelines so outcomes are inspectable instead of one-off chat.

Dark FactoryAEO Kit + AEO ConsoleKnowledge Engine

◆

UI as Operational Surface

Consoles and prototypes built as operator surfaces—dashboards, jobs, tuning, settings—not slide-only narratives.

AEO Kit + AEO ConsoleNexusAI PlatformAItunes

// closing

These systems represent a shift from documentation into AI-powered product architecture and operational platforms.

Explore All Systems