How Meta designed Muse: an AI agent people actually want to talk to | Alex Cornell (Design Director)

<p><strong>Alex Cornell</strong> is a design director at Meta, where he leads design on Muse, Meta’s consumer AI agent. He came to the role with a long background in software product design, including time as a founder, and has spent the past year building one of the most thoughtful agent interfaces in the consumer AI space. Muse ships with a custom avatar, a three-layer status display, a personalized ideas surface, and a generative feed. Alex has been sharing the reasoning behind each of those design decisions publicly on Threads.</p><p><br></p><p><strong>What you’ll learn:</strong></p><ol><li>Why Alex built Muse to feel like messaging, not an AI app</li><li>How Muse’s three-layer status system accommodates different levels of technical expertise</li><li>What generative UI actually means in a shipped consumer product</li><li>How Alex turned years of forgotten Instagram saves into a daily shopping catalog</li><li>Why his mom apologized to her Muse, and what it means for AI design</li><li>How he uses Muse to track his golf game, shot by shot, as he works toward a single-digit handicap</li><li>The mindset shift designers need when the output is never pixel-perfect</li><li>When to use the main chat versus a side chat, and where the architecture still falls short</li></ol><p>—</p><p><strong>Brought to you by:</strong></p><p><a href="https://workos.com/?utm_source=lennys_howiai&utm_medium=podcast&utm_campaign=q22025"><strong>WorkOS</strong></a>—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more</p><p>—</p><p><strong>In this episode, we cover:</strong></p><p>(00:00) Welcome and guest intro</p><p>(02:50) Designing Muse</p><p>(05:33) Choosing which primitives to surface: characters, ideas, feed</p><p>(08:50) Speed of model and response times</p><p>(11:01) Generative UI and personalization</p><p>(14:25) SkyMall demo: Instagram saves turned into a shopping catalog</p><p>(17:16) Shopping, monitoring, and price alerts with Muse</p><p>(19:07) Instagram and Pinterest connectors for visual data</p><p>(21:40) Golf use case: round recaps, shot data, practice breakdowns</p><p>(25:28) Main chat versus side chats</p><p>(27:56) Old blog turned morning podcast: 20 years of posts via the Wayback Machine</p><p>(29:39) Chess dashboard: game analysis with a snarky coach</p><p>(30:59) What designers need to learn for AI, and what still works</p><p>(34:33) Prompting strategy when Muse is being obstinate</p><p>(36:31) Where to find Alex</p><p>—</p><p><strong>Tools referenc