Design Director at Meta Superintelligence Lab working on Muse. Prev: Linear / Substack / Cocoon / Facebook / Dialpad / ISO50
San Francisco
Joined July 2008
- Tweets8.3K
- Following703
- Followers71K
- Likes7.3K
Pinned Tweet
Here is a walkthrough of Muse! Excited to share more about the personal agent we’ve been working on.
muse.ai
I’ll be speaking at @linear Orbit on December 9 in San Francisco.
Come by! Tickets at orbit.linear.app
Announcing the next round of speakers for Orbit (by Linear):
> Carl Pei (@getpeid)
> Alex Cornell (@alexcornell)
> Michelle Bu (@hazelcough)
> Zack Reneau-Wedeen (@ZackRW)
See the full agenda and request your ticket: orbit.linear.app
Looking forward to speaking with @soleio tonight!
This Tuesday at @SPC San Francisco
Design Chat X with @alexcornell at 5pm
Alex Cornell leads design of @Muse at @Meta Superintelligence Lab. A repeat founder and a design pioneer, Alex will share his unique vantage on the future of consumer agents.
Request access below.
You can design the entire Muse app just for you. With last week’s launch, you can make a space for anything you care about. And you can rearrange the app’s core navigation to create your perfect app.
Personal software.
I’ve got mine set up to support different personal gears: I have the app orientated around family and golf on the weekends, and work and news during the week. You don’t need to do anything fancy to get this working – just ask your Muse to set things up how you like. You can even ask for the tab bar to be removed, if you prefer.
In this video, you can see one of my spaces which I set up around memories. I wanted a place to reminisce and just asked for a daily grid of my Instagram stories. Simple, but it makes me smile every day.
I remember when we first prototyped this idea of a malleable app back in March. It was one of the most excited I’ve ever been about product development and it remains so.
Build a space for anything, plop it into your tab bar…with this update, you can completely reshape the app around what you care about.
You can customize each new space, and also the app’s structure itself. 🎨🛠️
Alex Cornell retweeted
This Tuesday at @SPC San Francisco
Design Chat X with @alexcornell at 5pm
Alex Cornell leads design of @Muse at @Meta Superintelligence Lab. A repeat founder and a design pioneer, Alex will share his unique vantage on the future of consumer agents.
Request access below.
Alex Cornell retweeted
Playing around with spaces in Muse lately -- tell Muse what you need and it builds it.
I've made a BBQ game, an event tracker, and a home control dashboard.
Excited to see what you build.
Alex Cornell retweeted
Now in the Muse app: talk with your Muse in real time. And pick from multiple voices 🗣️
Alex Cornell retweeted
preview of our @SPC design chat
Looking forward to jamming about design with @soleio on Nov 10th! Will be at South Park Commons in SF. Speaking secrets and spells.
Register here: luma.com/alex-cornell-spc
Looking forward to jamming about design with @soleio on Nov 10th! Will be at South Park Commons in SF. Speaking secrets and spells.
Register here: luma.com/alex-cornell-spc
Alex Cornell retweeted
Live Design Chat at @SPC SF
Tue 11/10 @ 5PM
@alexcornell × @soleio
Alex Cornell is a design director at @Meta Superintelligence Labs, where he leads design for @Muse. He’s a repeat founder and AI design pioneer.
This event has limited seats. SPC members and alum welcome! RSVP below.
Excited about this! And what a great lineup 🙌
SF Design Chats at @SPC are BACK:
Wed Nov 4 @iansilber
Tue Nov 10 @alexcornell
Tue Dec 8 @johnbai
Tue Jan 12 @mschoening
Alex Cornell retweeted
it's no secret I think that @Muse is the best personal agent for normies on the market right now
a lot of the magic comes from design, and I got @alexcornell to come on the pod and walk us through how meta designed everyone's favorite fuzzy AI.
in this ep we cover:
- why muse is more than a chatbot
- how progressive disclosure is the key to having powerful AI (without overwhelming users)
- Alex's personal use cases, including Sky Mall style shopping catalogs and deep analysis of his performance in golf and chess
plus, Alex tells us what designers need to think about as they step into this new non-deterministic world
full ep now on YT 👉 youtu.be/4TOLm1g-gCE
Really enjoyed speaking with @clairevo about the design of @Muse!
We discuss a bunch of the little design decisions we made along the way, along with a few of my workflows: youtube.com/watch?v=4TOLm1g-…
Alex Cornell retweeted
we launched muse a month ago today
for the past month, reality felt like a dream. we watched the world catch fire with muse. every day we read stories of people saving money and precious time. every day it made people’s lives better in small and big ways. every day i watched the muse team pour their hearts into bringing a little more wonder in the world.
the response to muse has surpassed anything i could have imagined. i know the muse team will remember it for the rest of our lives.
it is easy to become jaded in tech. products launch every day but they very rarely make any dent in the world. but i have seen muse make a real difference for moms, for grandpas, for students, for coworkers. many of you using it in ways we never expected.
thank you to the muse team. thank you to everyone who’s tried muse. this is only the beginning. we have so much more to build.
1/ today we're rolling out Muse, our new personal ai assistant. Muse is always-on, wicked fast, can use a browser, connect to your apps, and is designed to be secure.
try it now: muse.ai.
A distinctive feature of Muse is the tab bar. It was one of the first things in the initial prototype, and it felt like a foreign addition for an AI app. So foreign that I recall leaving on PTO early on and leaving one instruction: "do not remove the tab bar," knowing how tantalizing it would be to simplify the app by removing it.
Beyond ergonomics, the tab bar’s core benefit is framing. Agents are capable of more than people realize – the tab bar provides the surface area to expose that functionality and make it conceptually (and physically) accessible. Each tab does this in its own way.
Ideas is the most literal example. True to its name, the Ideas tab lists ideas from your Muse about how it can help you. This is a great way to learn about the many things Muse can do, especially for people who aren’t technical. At first the ideas are universal, but as your Muse gets to know you, its ideas become much more personalized and update frequently.
If Ideas shows you what Muse could do, the Goals tab shows you what Muse is doing – whether it’s helping you with a goal or keeping track of something. Muse does so many things that it helps to visualize it all as a kind of mutual to-do list where you can monitor status. Again this serves both a practical and conceptual benefit.
More thoughts to come, but I’m glad we kept the tab bar and I’m excited about how it will evolve time.
Alex Cornell retweeted
the muse hype is real. i can def say that it is the easiest to use & most focused consumer ai product on the market. the extremely generous limits also make it impossible to ignore.
it actually helps the avg person navigate the day to day complexity of personal life.
if you go back to my april tbpn appearance, i talked about how an ai generated feed would become a baseline primitive for new ai experiences & muse has a pretty compelling version of that idea already. & you can start to imagine how powerful the multiplayer layer could become.
my stack right now is claude for work & muse for life. great execution from facebook here. credit where credit is due.
One of the most fundamental decisions we made early on with @Muse, was to contain every message in a bubble, like a chat app. Attaching the earliest comparison I could find – showing no container vs. the initial bubble treatment we used.
A founding principle was that Muse should feel like an entity not a tool. It’s an agent! Not a search box. And one of the clearest patterns to imply this is a message bubble.
Ironically, years before, I had argued for the exact opposite model.
Beyond the visual, there are two reasons that this messaging-framing is so important: Muse exists in a canonical, single thread. And Muse is proactive.
Like messaging a person, there is no need for disparate threads*. Muse can handle growing context and multitask. This makes a single thread much simpler to manage and – just like a speaking with a person – a more natural exchange.
Proactivity is interesting, as it relates to bubbles. Given Muse can message you, the delineation of when it did so is uniquely important. It’s not turn-based! This makes the boundary between new messages more important than ever before. A bubble solves is a great solve for this.
*Before you say anything: side chats warrant their own post, and I’ll cover this at a later time.
2
54
6,040
I ended up taking the bubble thing a little too far, and for some time, everything that Muse sent appeared in a bubble container. The entire app sat on a wash, and everything was elevated using a white bubble and a grey stroke. Grey and a black stroke in dark mode.
Can I say, I loved this. I miss it dearly. I am weirdly obsessed with the way a black stroke looks on an almost-black wash. And I think elevating with white-on-grey in light mode is just superior.
But, indeed, it was visually complex to do it literally everywhere in the app. When taken as a whole, this approach was visually noisy.
It will have to be another post, but this design direction died a fiery death in one fateful meeting, which changed the visual direction dramatically. For another time..
