Selected work
AI workflows I've built for support.
Human-in-the-loop tools that handle the repetitive parts — search, summarization, verification — so people stay focused on judgment, empathy, and complex resolution.
AI Operations Copilot · Built for ApartmentIQ
Signal — AI Operations Copilot
A working prototype built specifically for ApartmentIQ's AI Operations Lead role: an AI triage-and-drafting layer for support tickets, CS call notes, sales call summaries, and data-quality complaints, with human review, confidence scoring, and an evaluation dashboard modeled on ApartmentIQ's real scale — 40M+ units tracked, 250+ proprietary collectors. Same human-in-the-loop pattern as my call-note and mispick workflows below, applied to a new domain.
LLM PromptingHuman-in-the-Loop QAEvaluation Dashboards
Human-in-the-loop AI · Featured
AI-Assisted Call-Note Drafting
A Gemini Gem that turns AI call-transcript summaries into clean, consistently formatted CRM notes — a Subject line plus a 1–3 sentence Call Summary. The rep reviews, edits, and posts. Designed to capture every relevant detail consistently without removing human judgment.
GeminiFive9 Agent AssistNetSuite
Prompt design
Customer Email Prompt Library
A prompt library that drafts brief, empathetic, ownership-driven customer emails — aligned to core CX values across delayed shipments, marketplace confusion, RMAs, refunds, and upset customers.
ChatGPTPrompt Design
Investigation · Human-in-the-loop AI
Mispick Verification & Part Search
An evidence-first investigation workflow that turns “you shipped the wrong item” into a root cause — true mispick, packaging change, vendor substitution, customer error, listing error, or variation confusion. Compares what was ordered against what was received, spec by spec, and classifies the case. Started as a Gemini Gem for verified part search; grew into a full mispick playbook.
Gemini GemOrder managementRoot Cause Analysis
Quality & CSAT
QA Call-Language & CSAT Playbook
Reusable call language for greetings, holds, ownership statements, transfers, and closings to improve consistency — plus tested closing language to lift CSAT survey participation.
QA StandardizationCSAT
Concept · Future state
AI Call-Coaching Dashboard
A proposed concept: an AI call-analysis surface (Plaud-style) that turns call transcripts into coaching signals — trends, recurring friction, and improvement opportunities for the rep and the team.
ConceptCoaching
Concept · Future state
"Apple-style" Agent Workspace
A proposed concept: redesigning the support agent workspace around clarity, focus, and intelligent triage — fewer tools, better signal, calmer work.
ConceptWorkspace Design