---
title: "How we Solved Agent Building"
category: "talks"
date: "2026-07-01"
time: "3:20pm-3:40pm"
track: "Harness Engineering"
room: "Main Stage"
speakers: ["Andrew Qu"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Harness Engineering"
scheduleRoom: "Main Stage"
scheduleLabels: ["Harness Engineering", "Main Stage", "session", "confirmed"]
---
# How we Solved Agent Building

## Conference Context
- Date/time: 2026-07-01 · 3:20pm-3:40pm
- Track/room: Harness Engineering · Main Stage
- Speaker(s): Andrew Qu
- Session type/status: session · confirmed

- Track: Harness Engineering
- Room: Main Stage
- Session type: session
- Status: confirmed

## Session Description
At Vercel I've built a successful AI data scientist, that has taken the load off of our data team from answering ad-hoc data queries, and fields over 1,200 unique queries a day from just internal Vercelians. I've been building and iterating on it since last september, and it's gone through over 6 different rewrites, the newest one of which has inspired us to build a new agent framework (to be teased during the talk ;) ). I'd talk about why we build agents, how we build agents, and how to build effective agents in today's world. Just prompting, to adding bespoke tooling, to embedding claude code, to file system agents, to skills-based agents, to the new agent harness framework.

## Media Evidence
No related AI Engineer channel video found yet.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
No linked video, transcript, or slide source has been attached yet.

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

## People
- [[andrew-qu]]

## Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.

## Synthesis
### Synthesized Breakdown
# How we Solved Agent Building ## Conference Context - Date/time: 2026-07-01 · 3:20pm-3:40pm - Track/room: Harness Engineering · Main Stage - Speaker(s): Andrew Qu - Session type/status: session · confirmed - Track: Harness Engineering - Room: Main Stage - Session type: session - Status: confirmed ## Session Description At Vercel I've built a successful AI data scientist, that has taken the load off of our data team from answering ad-hoc data queries, and fields over 1,200 unique queries a day from just internal Vercelians. I've been building and iterating on it since last september, and it's gone through over 6 different rewrites, the newest one of which has inspired us to build a new agent framework (to be teased during the talk ;) ). I'd talk about why we build agents, how we build agents, and how to build effective agents in today's world. Just prompting, to adding bespoke tooling, to embedding claude code, to file system agents, to skills-based agents, to the new agent harness framework.

### Speaker And Company Context
- [[andrew-qu|Andrew Qu]] — Chief of Software at [[vercel|Vercel]].

### Topics Covered
- [[coding-agents]]

### Derived Links And Source Material

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.