---
title: "Why AI Didn't Actually Make You Ship Faster"
category: "talks"
date: "2026-06-30"
time: "10:45am-11:05am"
track: "Expo Stage 3"
room: "Expo Stage 3 SW"
speakers: ["Gabriel Spencer-Harper"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Expo Stage 3"
scheduleRoom: "Expo Stage 3 SW"
scheduleLabels: ["Expo Stage 3", "Expo Stage 3 SW", "session", "confirmed"]
---
# Why AI Didn't Actually Make You Ship Faster

## Conference Context
- Date/time: 2026-06-30 · 10:45am-11:05am
- Track/room: Expo Stage 3 · Expo Stage 3 SW
- Speaker(s): Gabriel Spencer-Harper
- Session type/status: session · confirmed

- Track: Expo Stage 3
- Room: Expo Stage 3 SW
- Session type: session
- Status: confirmed

## Session Description
AI generates code faster than humans can review and verify it, and most engineering teams adopting codegen have hit the same wall: verification. In this session, Gabriel (CEO of Meticulous) breaks down why assertion-based testing has a structural ceiling that AI codegen has made impossible to ignore, what exhaustive verification actually requires technically (behavior capture, determinism, and backend isolation), and why the teams solving this now are the ones who will ship at the speed AI enables. The talk includes case studies from LaunchDarkly, which saw an 80% reduction in major frontend incidents after rollout, and Notion, which deployed verification infrastructure across every engineer on every PR to confidently adopt AI-generated code at scale.

## 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
- [[gabriel-spencer-harper]]

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

## Synthesis
### Synthesized Breakdown
# Why AI Didn't Actually Make You Ship Faster ## Conference Context - Date/time: 2026-06-30 · 10:45am-11:05am - Track/room: Expo Stage 3 · Expo Stage 3 SW - Speaker(s): Gabriel Spencer-Harper - Session type/status: session · confirmed - Track: Expo Stage 3 - Room: Expo Stage 3 SW - Session type: session - Status: confirmed ## Session Description AI generates code faster than humans can review and verify it, and most engineering teams adopting codegen have hit the same wall: verification. In this session, Gabriel (CEO of Meticulous) breaks down why assertion-based testing has a structural ceiling that AI codegen has made impossible to ignore, what exhaustive verification actually requires technically (behavior capture, determinism, and backend isolation), and why the teams solving this now are the ones who will ship at the speed AI enables. The talk includes case studies from LaunchDarkly, which saw an 80% reduction in major frontend incidents after rollout, and Notion, which deployed verification infrastructure across every engineer on every PR to confidently adopt AI-generated code at scale. ## Media Evidence No related AI Engineer channel video found yet.

### Speaker And Company Context
- [[gabriel-spencer-harper|Gabriel Spencer-Harper]] — CEO at [[meticulous|Meticulous]].

### 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.