
Andrew is the Chief of Software at Vercel, where he leads the company's agent initiatives across product, infrastructure, and internal tooling in the Office of the CTO. He's the creator of skills.sh, the most popular way to discover and install new agent skills, and is building "an agent on every desk" inside Vercel. The most prominent so far is a data science agent that fields 2,000+ questions a day from Vercelians across engineering, finance, and go-to-market. Before Vercel, Andrew founded a Series B AI sales-tech company, and has worked at Meta and early-stage startups alike.
Andrew Qu is Chief of Software in Vercel's Office of the CTO and the lead maintainer (#1 contributor) of Vercel's open agent-skills tool (npx skills, vercel-labs/skills) and mcp-handler; his recent talks and writing focus on the practical realities of shipping AI agents in production, including the counterintuitive lesson that cutting 80% of an agent's tools made it faster and more reliable. Attend for hands-on, data-backed lessons on agent architecture, MCP, and developer productivity from someone shipping these systems internally at Vercel.
How Vercel deploys internal agents at scale - Andrew Qu, Vercel | re:Invent 2025AWS re:Invent 2025 · Dec 2025
Vercel Skills Night SF 2.17.26 (featuring Guillermo Rauch and Andrew Qu)Vercel Skills Night SF · Feb 2026
Zero-Config MCP: The Framework-Independent Adapter - Andrew Qu, Vercel | MCP NightMCP Night · Jun 2025Public activity researched automatically · as of Jun 2026