Skip to content
How I AIHow I AI

Muse gets AI agent UX right

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. *What you’ll learn:* 1. Why Muse is the best-designed personal agent I’ve tested, and what specifically made it feel that way 2. The one-shot family PDF Muse produced that Claude and Codex never quite nailed 3. How Muse’s permission model works, and why it’s different from every other agent I’ve used 4. Why I set up a sleep training goal in Muse, and what it revealed about agent tone 5. The activity feed feature I immediately wished Codex and Claude Code had 6. Where Muse failed, and what it says about the limits of this category right now 7. The animated avatar decision that showed me what top-of-craft AI product design actually looks like *Brought to you by:* Optimizely—Your AI agent orchestration platform for marketing and digital teams: https://www.optimizely.com/howIAI OpenArt—An all-in-one AI creation platform for images, videos, music, audio, and more: https://openart.ai/suite/chat?utm_source=online&utm_medium=influencer&utm_campaign=infl-howiai-ga-na-acq-web *In this episode, we cover:* (00:00) What Muse is and who it’s actually built for (04:41) Signing in and the onboarding flow (07:16) The activity feed and its task lineage (08:24) First real task: managing the family calendar and deleting soccer practice (09:48) Requesting a morning newsletter PDF (14:29) The personalized news feed and how I set it up (16:05) The “Ideas” feature as an out-of-the-box prompt library (17:10) Setting up personal goals (water, shoes, and sleep training) (21:40) Library: documents, websites, images, videos, and podcasts (23:11) Quick recap and what I love (23:56) Activity feed design deep dive: tool calls and step-by-step lineage (25:18) How Muse handles permissions (26:12) The animated avatar: Polly becomes Slime, the teal dragon (29:34) Browser use test: shopping for New Balance 9060s (not great) (31:15) Browser use test 2: buying IMAX tickets for The Odyssey (much better) (33:34) TL;DR and what I’ll actually use Muse for going forward *Tools referenced:* • Muse: https://muse.ai/ • Stripe Link (payment method featured in Muse): https://link.com • 1Password (future Muse integration mentioned): https://1password.com • OpenClaw (Claire’s previous personal agent setup): https://openclaw.ai/ • Grok Bot (Grok-based agent from prior stack): https://x.ai/news/introducing-grok-bot • Codex (OpenAI coding agent, comparison point): https://openai.com/codex • NotebookLM (Google, comparison to Muse’s podcast generation): https://notebooklm.google.com *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Sep 16, 202637mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Meta’s Muse nails personal AI agent UX with trust and delight

  1. Claire reviews Meta’s Muse as a personal AI agent aimed squarely at parents (millennials/Gen X), emphasizing consumer-friendly UX over “developer” concepts like plugins, tools, or crons.
  2. Muse’s onboarding and permissions flow is a core differentiator, using progressive disclosure to build trust while still enabling real actions like connecting Google Calendar and deleting events.
  3. Muse’s best demo is generating a beautifully designed, printable “morning newsletter” PDF that combines family schedule logistics with local, kid-appropriate news and conversation prompts.
  4. Distinct UI primitives—Activity Feed with task lineage, personalized Feed, built-in Ideas library, Goals tracking, and a Library of generated artifacts—make the agent feel complete and easy to use.
  5. Browser automation is uneven (shoe shopping struggled; IMAX ticket-buying succeeded), but overall Claire calls Muse her favorite agent UX in a long time and plans to use it for wellness, kid logistics, and daily briefs.

IDEAS WORTH REMEMBERING

5 ideas

Muse’s standout strength is consumer-grade trust UX (permissions + transparency) rather than raw model power.

Muse immediately anchors the experience in trust-building: clear “few things to know,” explicit approval moments, and progressive disclosure of what it will access and why. Claire highlights that it asks to read email, then confirms what it learned, then asks permission to use those inferences—creating confidence without becoming annoying.

The Activity Feed makes agent behavior legible through task lineage and tool-call traceability.

The Activity Feed doesn’t just list past tasks; it shows step-by-step lineage (tool calls/scripts) in a UI that both consumers can skim and power users can inspect. Claire calls this “show the work” transparency that she wishes existed in tools like Codex and Claude Code.

Artifacts (especially PDFs) are a “delight” moment—highly readable, family-friendly outputs that fit offline life.

Muse successfully turns calendar + email context into a polished, printable one-page “morning newsletter” PDF with schedule, kid-specific callouts, conflicts (e.g., overlapping activities), local/kid-appropriate news, and dinner-table prompts. Claire notes this is the first time she’s gotten a one-shot design she actually likes compared to prior attempts in other tools.

Muse’s primitives—Ideas, Goals, Feed, Library—reduce prompt burden and make personal-agent use cases feel native.

Instead of requiring users to invent workflows from scratch, Muse ships with “Ideas” (a built-in prompt library) and “Goals” (personal goal tracking with nudges). Claire finds Goals especially well-designed for wellness and life admin—more supportive than a generic chat thread.

Voice + micro-interactions matter: Muse feels emotionally appropriate and intentionally designed.

Claire praises Muse’s tone as gentle, human-first, and non-sycophantic, especially in sensitive contexts like sleep training. The animated avatar and micro-interactions (laptop while working, orb during media generation) reinforce clarity and delight without feeling like “rounded buttons” superficial polish.

WORDS WORTH SAVING

5 quotes

This is for millennials with kids, maybe Gen X with kids. This is for the olds.

Claire Vo

I don't want agents that get me on my computer. I don't want agents where my face is in the phone. I want agents that get me with my family into my life in an offline way.

Claire Vo

It's not that it's the most intelligent, it's not that it has the most powerful, um, it is just so well designed.

Claire Vo

Sleep depri- deprivation with a baby is its own special kind of hard. We'll get you some rest.

Muse podcast/agent voice

When I talk to designers about operating at the top level of your craft, I do not mean rounding buttons. I do not mean making strokes. I do not mean running impeccable. What I mean is this.

Claire Vo

Target audience: parents/millennials/Gen XOnboarding and sign-in via Meta ecosystemPermissions and progressive disclosureActivity Feed task lineage and transparencyCalendar management (deleting soccer practice)PDF “morning newsletter” artifactPersonalized news Feed setup prompting style guide (no clickbait)“Ideas” as prompt library / guided use cases,

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.