How Meta designed Muse: an AI agent people actually want to talk to | Alex Cornell (Design Director)
- ID
- 34451
- Status
- summarized
- Published
- 12 Oct 2026, 8:03 PM
- Fetched
- 12 Oct 2026, 8:21 PM
- Provider
- Lenny's Newsletter
- Category
- product-startup
- Original URL
- https://www.lennysnewsletter.com/p/how-meta-designed-muse-an-ai-agent
- Source URL
- https://www.lennysnewsletter.com/feed
Summary
- Score
- 6.5
- Created
- 12 Oct 2026, 8:22 PM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Alex Cornell, who leads design on Meta's consumer AI agent Muse, walks through the shipped interface decisions: a custom avatar, a three-layer status display intended to serve a non-technical parent and an engineer through the same UI, a personalized ideas surface, and a generative feed. Demos include turning years of forgotten Instagram saves into a SkyMall-style shopping catalog, piping 20 years of blog posts through the Wayback Machine into a morning podcast, shot-by-shot golf round recaps, and a Chess.com dashboard with a snarky coach. He also covers when to use the main chat versus a side chat, and where that architecture still falls short.
Why it matters
The transferable pattern is progressive disclosure: one agent interface with layered status detail instead of separate beginner and expert modes, plus Instagram and Pinterest connectors used as raw material for generated surfaces. It is a design interview, not a release — there is no new API, price, or availability change to act on, and nothing Malaysia-specific in the episode, so treat it as design input rather than a build trigger.
Discussion angle
Take the main-chat-versus-side-chat split: when does branching a conversation beat one long thread, and what breaks in your own agent when state has to live in two places at once?