Projects

A working sample of the systems I build: some shipped to production, some still proving themselves out.

Retrieval Evaluation Harness

Production

A scoring framework that grades RAG retrieval quality against a labeled query set, so retrieval changes get judged on precision and recall instead of spot-checking a few answers by hand.

RAGEvaluation

Python · pgvector · pytest

Read the case study →

Support Ticket Triage Agent

Production

Classifies incoming support tickets, drafts a first-pass response, and escalates anything below a confidence threshold to a human, instead of trying to automate everything.

AgentsAutomation

TypeScript · Cloudflare Workers · Queues

Read the case study →

Structured Extraction Pipeline

Production

Turns unstructured PDFs and emails into structured records with per-field confidence scores, routing low-confidence extractions to a review queue rather than guessing silently.

ExtractionDocument AI

Python · Workers AI · D1

Read the case study →

Prompt Regression Test Suite

Production

CI-integrated testing for LLM-backed features: every prompt or model change runs against a fixed set of cases before it can merge, catching silent quality regressions.

EvaluationTooling

TypeScript · GitHub Actions

Internal Knowledge Assistant

Prototype

A RAG chatbot over internal documentation that cites its sources inline, built to be honestly wrong sometimes rather than confidently wrong always.

RAGInternal Tools

Workers AI · Vectorize · React Router

Underwriting Memo Drafting Assistant

Research

Drafts first-pass risk memos grounded strictly in supplied source documents, with numeric claims traced back to a citation. Human underwriters review and sign off on every memo.

LLM ApplicationFintech

Python · Structured Outputs

Read the case study →