Claire Vo · 2 min read · Design
Muse review: The personal AI agent that gets consumer UX right
Read the original on lennysnewsletter.com →
In this hands-on review, I tested Meta’s Muse personal AI agent across onboarding, calendar management, goal setting, and more, including a one-shot family newsletter and browser shopping. The piece argues Muse is the best-designed personal agent tested so far, thanks to a thoughtful permission model, a compelling animated avatar, and a transparent activity feed, while also noting current limits and areas for improvement.
Key Takeaways
- Muse's onboarding, permissions model, and tone create a delightful, trusted user experience that outshines prior agents.
- The activity feed with task lineage provides transparency into the agent's steps and decisions, plus a built-in prompt library like 'Ideas' for quick enhancements.
- Muse's one-shot family newsletter PDF demonstrates advanced content generation capabilities that outperform comparable agents on this task.
- The animated avatar design (Polly becoming Slime) showcases how top-tier product design can elevate user perception of AI intelligence.
- Real-world friction points—especially browser-based shopping—reveal the current limits of personal AI agents and where improvement is needed.
Excerpt
I spent a few hours putting Meta’s Muse, its new personal AI agent, through a real first-pass test: onboarding, calendar management, goal setting, a one-shot family morning newsletter, browser-based shopping, and the animated avatar that honestly surprised me. Listen or watch on YouTube , Spotify , or Apple Podcasts What you’ll learn: Why Muse is the best-designed personal agent I’ve tested, and what specifically made it feel that way The one-shot family PDF Muse produced that Claude and Codex never quite nailed How Muse’s permission model works, and why it’s different from every other agent I’ve used Why I set…