Skip to content

Work

Systems that use AI, and keep a person in control.

These projects exist because I understood the problems before I understood the implementation. Agentic CRM is the flagship; an AI construction estimator and Honors research sit alongside it. Each is described at the stage it's actually at: what works today, and what comes next.

Agentic CRM

Core operational · final validation

A multi-tenant CRM that reads a team's inbox, proposes the next CRM action, and executes only what a person approves.

Keeping a CRM current is manual upkeep, and manual upkeep slips. Records fall behind, and the system of record everything depends on goes stale.

Core CRM, workspace isolation, Gmail sync, the AI approval flow, auth, and billing are operational. Current work is deployment: containerizing the services, deploying onto Kubernetes, adding observability, and hardening before a small private beta.

Selected stack
FastAPI · PostgreSQL · Redis · React · TypeScript · Docker · Kubernetes · Gmail OAuth
Read the case study

  • AI Construction Estimator

    Early build · in development

    An AI-assisted takeoff tool that reads construction plans, drafts measurements, and leaves every number for an estimator to check.

    Early build. Document-understanding and computer-vision workflows read plans and extract measurements into a reviewable takeoff, with the estimator in control of every figure.

    Stack
    Python · FastAPI · Computer vision · PostgreSQL · React
    Read the overview

  • Decision-systems research

    Active Honors research · methodology in design

    Honors research comparing how quantitative, human, and AI decision frameworks perform when replayed on identical market history.

    A framework-agnostic simulation harness is being built to replay decades of history under each framework. Large-scale evaluation runs are designed but not yet run.

    Stack
    Python · Applied mathematics · ML · Simulation
    Read the research