Why AI Didn't Actually Make You Ship Faster — Gabriel Spencer-Harper, Meticulous

AI writes code faster than humans can review it. Verification is now your bottleneck. Gabriel Spencer-Harper, co-founder and CEO of Meticulous, explains why assertion-based tests can't keep up with AI-generated code, and what near-exhaustive frontend verification with zero developer effort looks like. He demos how Meticulous records real user flows, replays them on every pull request and shows visual before/after diffs. He also explains the three technologies that make it work: fully mocked network traffic, a deterministic browser and coverage-guided flow selection. In this talk: • Why the space of possible regressions is too big for hand-written assertions • How record-and-replay visual diffing works on every PR • Making the browser deterministic to eliminate flaky tests • Why code coverage finally means 'code tested' when you screenshot every step SPEAKER Gabriel Spencer-Harper, Co-founder & CEO, Meticulous LinkedIn: https://www.linkedin.com/in/gabrielsharper/ LINKS Meticulous: https://www.meticulous.ai CHAPTERS 0:00 Intro 0:12 Meet Gabe 0:27 Verification is the new bottleneck 1:12 What Meticulous does 1:47 AI writes code faster than we can review it 2:07 Why assertion tests aren't enough 2:27 Would you hit merge on this PR? 3:01 The cost: bugs, flaky tests, lost time 3:46 What exhaustive verification unlocks 4:16 Demo: record and replay 5:51 Reviewing visual diffs on a PR 7:11 How it works: mocked network 8:01 A deterministic browser 8:41 Coverage-guided flow selection 9:25 Why code coverage finally means something 10:45 Wrap-up Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #AICoding #Testing #AIEngineer