AI & Data Portfolio
Building intelligent systems from inside the enterprise
I build AI agents, classification pipelines, and analytics systems that turn manual workflows into automated ones — shipping production tools used by real enterprise teams.
About
8+ years in enterprise adtech and SaaS, specializing in API integrations and measurement systems. I build AI-powered tools — agents, pipelines, and dashboards — that turn manual workflows into automated ones. Targeting AI-adjacent roles in Solutions Engineering, Product Ops, and GTM Enablement.
Impact at a glance
→ 30 min monthly reporting automated
Projects
Case Intelligence System
End-to-end support case analytics pipeline turning raw CRM data into structured monthly insights for a high-volume product area. Built a 9-category symptom taxonomy, an automated LLM classification pipeline with confidence scoring, and an interactive stakeholder dashboard — reducing report production from 4–6 hours to ~30 minutes and creating a documented handoff framework so institutional knowledge survives role transitions.
OKR Tracking Dashboard
Used an enterprise AI analytics agent to build a dual-view interactive OKR dashboard — a leadership-facing status view and a personal IC competency-tagged view — sourced live from structured documents. Generated evidence packages for performance reviews through natural language interaction.
AI Campaign Feature — Launch Readiness
Led bug bash and cross-functional coordination for an enterprise AI-powered campaign audience feature. Identified critical bugs affecting strategic accounts, opened engineering tickets, and produced the go-to-market one-sheeter that ensured field readiness during a critical launch window.
Ticket Duplicate Detector Agent
Presented at a company-wide internal hackathon. Proposed a Glean-based agent to identify duplicate engineering tickets before creation, saving an estimated 20 min/instance across the support org. Engineering leadership expressed interest in productionalizing — opportunity sizing initiated with the product platform team.
Newsletter Intake Assistant
Glean Workflows agent automating discovery, filtering, and packaging of sales-relevant product updates for a biweekly internal newsletter. Searches defined sources with sales-facing keywords, categorizes into "Need to Know," "Coming Up," and "Tips," and outputs consistent summaries. Validated in pilot with positive stakeholder feedback.
Healthcare Domain Classifier
AI agent that inspects advertiser domains across key site sections, applies help center and internal policy rules, and outputs consistent B2B vs B2C decisions with embedded next steps — distinguishing legal escalation paths from standard rejections. Built for auditability and reproducible outcomes. Received strong SME endorsement at review.
Engineering Ticket Intake Assistant
Agent that reads internal escalation threads and outputs a structured ticket package for engineering handoff: title, description, expected vs. actual behavior, and supporting references. Eliminates manual copy-paste handoffs and enforces consistent documentation quality across the escalation chain.
OKR Objective Categorization Agent
Takes user-listed objectives, pulls role context and project artifacts, writes SMART key results, and buckets each by impact/probability (Big Bet / Home Run / Small Win / Junk) — outputting a structured planning table. Replaces hours of manual planning review and formatting.
Peer Review Assistant
Calendar-aware feedback agent that determines the correct review cycle window, pulls collaboration artifacts from the relevant period, and produces structured, compassionate feedback (start/stop/continue) with supporting evidence and resource links — aligned to company review frameworks.
AI Campaign Performance Calculator
Glean AI agent that automates average-clicks-per-day calculation across campaigns, normalizes engagement over time, and outputs structured performance summaries with multi-campaign table comparison — eliminating repetitive manual calculations in support workflows.
Skills & tools
- Glean Workflows agent design
- LLM context engineering
- Multi-label classification
- Confidence scoring & validation
- Anti-hallucination constraint design
- SQL (Trino / Hive)
- Salesforce data modeling
- Case volume & resolution analytics
- Anomaly detection
- Time series & MoM trend analysis
- Taxonomy design & evolution
- Interactive dashboards (Chart.js, Plotly.js)
- Executive reporting & storytelling
- Tier segmentation analysis
- Product feedback translation
- Knowledge management & runbooks