AI & Media Operations

What I do

I work at both levels of media operations: supervising specialists, priorities, and escalations while staying close to the assets and decisions themselves. That combination shapes how I design AI-assisted workflows—useful to the people doing the work, legible to the people accountable for it, and honest about where human judgment still matters.

• Operations leadership: priority setting, escalations, training, quality metrics, tool testing, and workflow improvement
• Streaming QC and localization: video, multitrack audio, timed text, metadata, delivery troubleshooting, and Mandarin-language APAC content
• Applied AI: Johns Hopkins work in prompt design, retrieval, evaluation, and human-reviewed decision support

How I approach AI

My approach to AI begins with the operational problem: where assistance would be useful, what good performance looks like, and what should remain under human control. My applied-AI studies at Johns Hopkins, along with Anthropic’s AI Fluency: Framework & Foundations ↗, have sharpened that practice—particularly the importance of clear context, evidence-based evaluation, privacy, and downstream consequences.

I use OpenClaw, an open-source platform for building and operating AI assistants, to put those principles into practice. It helps me coordinate research, prototypes, documentation, and personal workflows across models and tools. Just as importantly, it requires practical decisions about permissions, memory, approval boundaries, auditability, and recovery when something fails.

I’m not interested in automation for its own sake. The goal is AI that helps people retrieve, compare, draft, and think while making uncertainty visible and leaving accountable decisions with humans.

Selected work