Projects
Selected work
Internal tools I built to solve real problems for my teams at Unity, plus a few personal experiments.
Work tools

Screenshot shows sanitized example data, not real customer or employee information.
AI Ticket Triage & Insight Dashboard
Internal ToolInternal dashboard for Unity's Partner Relations team to self-serve open tickets and years of historical customer engagement notes, replacing manual searching with fast, filterable views. Powered by a resumable async batch pipeline using the Anthropic SDK to distill thousands of raw records into concise, LLM-generated summaries.
Cut ticket search time from 10 minutes to 30 seconds, and made years of historical engagement notes, previously unsearchable, findable in seconds.

Screenshot shows sanitized example data, not real customer or employee information.
Customer Story Intelligence Pipeline
Internal ToolA dashboard and companion CLI that turn raw field anecdotes from Unity's Partner Relations team into polished, leadership-ready narratives. Uses a streaming LLM pipeline to draft copy and a rubric-driven LLM-as-judge step to flag quality gaps before anything reaches an executive audience.
Used for a month to produce exec-facing customer stories, sustaining a rate of 4 stories per week.

Screenshot shows sanitized example data, not real customer or employee information.
Partner Radar: Customer-Matched Update Feed
Internal ToolInternal web app for Unity's Partner Relations team that surfaces engine, platform, and program updates, prioritized so nothing important gets lost in Slack noise. Each update is matched to the specific customers it actually affects based on their tracked tech stack, with ingestion running as a scheduled AI agent job.
Matches platform updates to the customers they actually affect, cutting missed-update risk for a team managing $6M+ in ARR.

Screenshot shows sanitized example data, not real customer or employee information.
Guided Self-Review Assistant
Internal ToolA lightweight guided web app that walks employees through structured mid-year self-reflection questions one at a time, then uses an LLM to draft polished, evidence-based answers covering accomplishments, growth areas, and feedback for leadership. Built as a dependency-free vanilla JS front end with an iterative refinement loop and a regional variant for distributed teams.
Cut mid-year self-review drafting time from about 2 hours to 30 minutes.
Personal experiments

A bilingual marketing site for a premium short-term rental in Cali, Colombia. An autonomous content pipeline sources imagery, drafts bilingual captions, and publishes on schedule, with human approval built in via a password-protected admin dashboard.