Gui Seiz and Alex Kern from Figma walk through the exact workflow they use to keep design and code in continuous sync using Figma’s MCP, Claude Code, and Codex. Their demo shows the full round-trip: pull a running web app into Figma as editable frames, make design changes on the canvas, push them back to code via Claude Code. If you’d rather read than watch the full video, the newsletter summary of this How I AI episode captures the key takeaways.
Meng To shares a concrete end-to-end workflow where OpenClaw runs as a local “agency layer” that talks to files, shell, browser, and Telegram, while Codex acts as the focused coding specialist for real repos and multi-task queues. He replaced tools like Notion, Midjourney, Cursor, and v0 with local Markdown files, Nano Banana Pro API, and four specialized Telegram bots to compress a 3‑month and 5–10 person product cycle into about a week while working solo. This setup is powerful but requires non-trivial security setup, careful prompt and reference management, and still leans heavily on code review and system hygiene rather than “hands‑off” autonomy.
Theo shares a 22-minute demo of OpenAI’s new Codex desktop app, pitching it as a “Cursor killer” after using it for a week of real work.
Ed Bayes from Open AI shared a 2 minute demo of using the Codex desktop app’s Figma skill to turn designs into front-end code with 1:1 visual parity, including all CSS classes and styling.