Intel / article

Vercel's Andrew Qu on why agents are a new kind of software

Source: latent.space
Author: Richard MacManus
Date: Published Jul 3, 2026

Context

Vercel built its eve framework around problems it encountered running agents internally. Chief of Software Andrew Qu describes needing to switch model providers, fall back when necessary and resume interrupted work. Collecting those capabilities into reusable software was meant to spare other developers from repeating the same exploration.

Qu's account also explains why autonomy needs to vary by task. Work with a clear endpoint may suit a continuing automated loop; delicate engineering changes need more frequent human steering. The framework supplies machinery for sustained work, while the application designer still chooses when the agent should return for feedback.

Terms in this piece · Glossary

AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.

Key quotes

“I think agents are a new type of software. They are not as predictable as web applications.”
Andrew Qu

“A good candidate is often a repetitive task that still requires some reasoning.”
Andrew Qu

“Until companies can audit and update every old piece of content, skills provide a way to forward-correct the model.”
Andrew Qu

“We have published reports showing bot traffic rising while human traffic is stagnant or declining, even as impressions increase, because agents and bots are hitting websites more frequently.”
Andrew Qu

“At Vercel, we already detect when an agent makes a request and serve Markdown directly.”
Andrew Qu

Read the source www.latent.space