AI Operations · Enablement · GTM Ops

I ship agents. Then I watch them work.

Independent AI practitioner building production-grade agent systems — with the retry logic, evals, and runbooks most demos leave out. Formerly PM at AWS, Chief of Staff at an early stage fintech startup.

Featured systems

Not just working demos

Each one ships with the failure modes documented, a quality gate, and an answer to "how do you know it's still working."

Shipped

AI Lead Research Brief Generator

Turns a company name into a validated lead brief in seconds — replaces 30–45 minutes of manual SDR research.

web search CoT pain extraction Pydantic-validated output retry on schema failure
$0.009 / briefSchema-validated retry loop
PythonClaude APIPydantic
Shipped

Client Onboarding Automation Agent

Classifies incoming client type, routes to the right checklist, then runs contract, workspace setup, and kickoff drafting in parallel.

classify route to worker parallel execution re-run if score < 7/10
$0.006 / package9 client typesMulti-threaded
PythonMulti-threadingEvaluator-optimizer
Migrating off spreadsheets

Agent Observability Platform

The system that answers "how do you know your agents are still working" — one live view replacing four separate spreadsheets: run health, eval scores, incident runbook, and weekly reporting.

status: currently Google Sheets + n8n · rebuilding as a standalone app
Per-run cost & latencyLLM-as-judge quality scoreThreshold-based alerting
n8nSheets APILLM-as-judge evals
Shipped

Nonprofit Grant Research & Writing Agent

A stateful agent that finds grant opportunities, retrieves matching RFPs, and drafts narrative sections — remembering prior applications across sessions.

IDLE SEARCHING RETRIEVING DRAFTING AWAITING_EVAL DONE
Targets 10–20 hrs saved / cycle
PythonChromaDBRAG
Shipped

Autonomous Competitor Intelligence System

Four specialized worker agents — news, reviews, pricing, feature diffs — synthesized into one weekly competitive brief with traceable sourcing.

4 workers (RAG-backed) synthesis agent weekly brief
Tested live on 7 named competitors
PythonMulti-agentRAG
Stack

What it's built with

Python Claude API n8n Pydantic ChromaDB Google Sheets API GitHub Actions Vercel
About

Operator background, builder habits

I spent my career in operating roles before I spent it in code — running product at AWS, and previously as Chief of Staff inside a Series A fintech lender. That's the lens I bring to agent systems: the question isn't whether it works once, it's whether it keeps working.

Now I build and operate AI agent systems with the eval loops, retry logic, cost and monitoring layer that make them safe to hand off.

Education
MBA, Wharton · BS Economics, Carnegie Mellon
Prior roles
Senior PM, AWS · Chief of Staff, fintech lending · GTM, Morgan Stanley
Currently
Building agent systems, open to AI Ops / Enablement / GTM Ops / Chief of Staff roles