Projects

Engineering deep dives

Systems at the intersection of trading infrastructure, AI tooling, automation, and product architecture — written for the engineering decisions behind the work, not just the visible feature list.

Structor

Public · Open source

Local-first Harness Engineering Framework for AI-assisted software teams. Structor generates repository-local governance, contracts, context routing, and validation layers for Codex, Claude Code, and similar coding agents.

Developer ToolingAI GovernanceAgentic DevelopmentLocal-First InfrastructureCLI Framework

Most tools organize prompts. Structor makes AI-assisted development more legible by giving repositories a local, reviewable operating surface for humans and agents.

Engineering Deep Dive Structor website GitHub repository

AI Front Desk

Public · Portfolio case study

AI-native SaaS prototype for small-business front desks: tenant onboarding, website ingestion, generated profile review, embeddable widget delivery, usage limits, and billing hooks.

AI Product EngineeringMulti-Tenant SaaSEmbeddable WidgetFull-Stack ArchitectureAutomation

The interesting work is the product system around the assistant: onboarding, ingestion, review, tenant configuration, runtime limits, and a widget that can live on another website.

Architecture NotesCase study

Crypto Copilot

Public · Portfolio case study

Simulation-first trading copilot that combines market data normalization, schema-constrained AI trade planning, guardrails, and simulated execution across a Next.js/FastAPI architecture.

Trading InfrastructureAI Decision SupportFastAPINext.jsSimulation-First Systems

The system explores the right boundary for financial AI: structured decision support over real market context, with validation before anything reaches even simulated execution.

Technical Deep DiveCase study