• token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
• guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.

Every prior attempt at syncing design tools and generated code lost fidelity in one direction; a drift-detection layer that catches dropped bindings and accessibility regressions targets a real gap in current AI design-to-code workflows.

• 0:00Losing the speaker notes, and what a roundtrip means
• 2:10Thirty years of handoffs that never closed
• 3:37Going all in on vibe coding
• 5:27The innerHTML moment that made him read the code
• 6:20Testing the claim that the roundtrip is solved
• 7:40A harness with code on one side, design on the other
• 9:33Show drift, accessibility, and what it catches
• 11:50Deterministic guardrails versus pure model output
• 14:06Human in control, not just in the loop
• 16:25Nine dimensions, and trying it yourself

• videoGenerative UI... in Python? — Jeremiah Lowin, Prefect
• videoDesign at the Speed of Adjectives — Paul Bakaus, Renaissance Geek, Inc.
• videoTraining Taste — Thais Castello Branco, Taste Labs
• videoMousepower: agents that can’t be measured, can’t be managed. — Maximillian Piras, Yutori

• videoDesign at the Speed of Adjectives — Paul Bakaus, Renaissance Geek, Inc.AI Engineer
• videoHarness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayerAI Engineer
• videoHow to Kill the Code Review — Ankit Jain, AviatorAI Engineer

Checking sign-in…

Loading comments…