Sara Rowghani (@sarar) header
Sara Rowghani (@sarar) profile picture

Building @dreamer. Furniture maker. Lover of puns.

New York
Joined January 2007
Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)Photo by Sara Rowghani (@sarar)
Sara Rowghani 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.
376
157
94
2,611
269,750
Sara Rowghani retweeted
Introducing Voice. Talk to your Muse and Muse talks back, so you can go from “what should I cook?” to cooking, just like that ✨
187
309
181
3,525
496,593
Sara Rowghani retweeted
dress for the job you want
57
39
5
676
37,347
Sara Rowghani retweeted
charmed to meet you!
555
492
564
8,623
3,266,584
Sara Rowghani retweeted
It’s funny, Meta went from having my Instagram and WhatsApp data to now having access to my email, calendar, DoorDash, Amazon and pretty much everything. In the last 24 hours, it bought me socks, ordered my Whole Foods groceries, booked a cleaning service and got me a burger for dinner. Meta’s last disclosed North American Facebook ARPU was around $227/year, largely from ads. I suspect it can push that number significantly higher now that it understands not only what I look at, but what I need, what I buy and what I’m planning to do. Also the much bigger opportunity might be becoming the aggregation layer between me and the entire internet. If Meta can take even a tiny percentage of the commerce it facilitates, or of the money it saves me, this could become enormous! It already saved me $200 by canceling subscriptions and services I no longer needed. This feels much bigger than better ad targeting. Ads are useful but giving me money back is better imo. One additional thought: the agent is increasingly making the decisions for me. I knew nothing about that burger place. The agent researched it, told me which burger I should order, and I just said “okay” without giving it much more thought. Agents are becoming the decision makers in both B2C and B2B. Increasingly, every business will be selling not just to humans, but to their agents. Everything becomes B2A: business to agents.
229
150
162
3,081
1,359,646
Sara Rowghani retweeted
I've been using the @Muse app on my Mac all day, every day for a while. There are four things it does that I really love: 1/ Quick access to my Muse when I'm working in any other app: ⌥–Space and Octavian appears, ready to help. 2/ Fast SOTA dictation into any app on my computer by holding fn (these shortcuts are configurable, ofc). 3/ The Muse app works with the messaging apps on my computer and helps me keep up. Sorry if I ghosted you before; I can never keep on top of my messages. Muse is already making me a better texter. 4/ My Muse has a little bot status pill that hangs out in the corner and tells me what Octavian is up to on my behalf all day long. What are you using the Mac app for?
muse for mac is HERE!! your agent can now get stuff done right on your computer — files, messages, calendar, notes, all of it. you're in control of what it can access, and it always asks before doing anything sensitive. Add it to the dock - ai.meta.com/muse/download/
19
6
6
205
37,325
Sara Rowghani retweeted
Meta's @Muse is the best personal agent I've tried to date. It actually save me $800+ a year on my cable and phone bills, which is just insane value for a free AI agent. Here's my new video where I walk through 10 of my favorite Muse use cases, including a personalized morning news feed, a habit tracker, and how I got Muse to call customer support and negotiate my bills for me. Honestly, I can see Muse becoming Meta's next billion-user app. 📌 Watch now: youtu.be/eU1ICyI9bCs
137
81
25
1,327
2,668,254
Sara Rowghani retweeted
Superintelligence this, superintelligence that... How about super-sick dancing @muse
38
31
27
583
174,358
Sara Rowghani retweeted
what are your top muse feature requests?
1,329
36
41
1,383
372,265
Sara Rowghani retweeted
You can customize your @Muse avatar and share it! Try it now on muse.ai/join
4
7
3
47
55,462
Sara Rowghani retweeted
i have a bunch of questions when i read, but want to stay screen-free my solution: connected my new @Pebble ring to my @Muse i send my agent off on a rabbit-hole & get the answer when im done with my article. phone stays in other room
2
4
1
39
3,910
Sara Rowghani retweeted
Meta gave me early access to Muse, their new personal AI agent. I did some wild things with it in my business and personal life. Genuinely super impressed with it. It just works. For example: it paid my bills, bought flowers, and booked date nights. This is what OpenClaw should have been.
24
13
6
269
32,990
Sara Rowghani retweeted
muse can help you be a better friend!
Found the killer use case for Muse lol
23
5
2
309
35,950
Sara Rowghani retweeted
our muse security architecture enables a ton of control over when the agent needs to ask for human-in-the-loop approval see more from the goat @bigT_sheesh:
In the blog post and video (research.meta.ai/blog/securi…) I posted earlier this week on the @Muse security architecture, we touched on the Sentinel and Human-in-the-loop. This extends to more than just regular web requests and protocols (HTTP/HTTPS), you can actually use a whole load of TCP/UDP based protocols. Check them out (on web muse.ai) under: Settings > Permissions > Direct network protocols > Profit! When you turn a protocol on, your Muse will send you a Human-in-the-loop approval card with the hostname and port, and you can control the permission allowance for your Muse. Give it a try and sent us feedback.
28
18
1
298
45,815
Sara Rowghani retweeted
the early usage on muse has blown way past our projections. muse’s users today are using 10x more than our testing cohorts. enjoy!
219
102
49
3,377
297,595
Sara Rowghani retweeted
muse, built for moms ❤️
NGL, $META genuinely may has just dropped an AI assistant for the masses. My mom could use Muse effectively and she’s never touched a chatbot in her life. Amazing job. Amazing product. It is user friendly, intuitive and has delivered everything I have prompted as I intended it with no re-direction. and on a cost basis, muse has delivered cheaply what has one shotted other token budgets. 👏🏻👏🏻👏🏻
45
13
7
529
62,706
Sara Rowghani retweeted
Pro-tip: ask your Muse to organize your IG saves for you
Replying to @alexandr_wang
2/ there are unique connectors that are only available to Muse like Instagram (incl dm’s), Threads, Facebook (incl marketplace), and Messenger.
14
10
1
310
27,460
Sara Rowghani retweeted
Muse is out today. An agent like this is a different kind of system to design. It reads your mail, spends your money, runs your code. Getting that right took real care, and our technical post walks through exactly how. We designed security in.
44
67
24
1,124
326,156
Sara Rowghani retweeted
every saturday my kids ask: is there a new @nbcsnl tonight? it's surprisingly hard to figure out. NBC's website is a maze. so i built a @dreamer agent in 20 mins so that I always know. host, musical guest, everything. try it: link in comments 👇 (it’s @Harry_Styles this week)
2
2
1
7
806
Sara Rowghani retweeted
Hey Andrew, a friend showed me your tweet this morning and it's a great fit for @dreamer . Here's an agentic app I built. I used your original tweet as the first prompt and it one-shotted something immediately useful. In @dreamer the understanding and knowledge of me is already there. My new agent started asking my sidekick to score and prioritize email and draft responses right away.
what's the current best approach on an AI that can help me handle my email inbox? seems like a big opportunity for folks playing with openclaw. For all of us who are drowning in email, this seems like a tier one problem that would be amazing to solve. (And I think I would pay $150k/year to have this product? I bet I'm not the only one) what I want is: - watch my inbox and process emails as they come in - score each message to see if it seems important (look at the sender, the topic/body, if its addressed to me or a big list, if I've ever replied to the sender before, etc etc) - read the email and reference a vast DB of knowledge that's been assembled already (based on my work, meeting notes, what I've replied on, etc), and decide what to do - reply with a draft note. For now, don't send, so that I can review the email -- but in the future maybe there's a YOLO option (but it would probably disclose that it's my assistant writing) - if less important, label it and file away. Eventually gather summaries for all of these less important emails and send me a summary of all of them with links to get back to it - or archive if it seems unimportant - or unsubscribe / mark spam / block if random marketing - if critical send me a notification right away so I can take a look I've played around with a bunch of the current AI tools and nothing quite works like this. There's a lot of blockers: - first, it needs 1000x more context about each problem, which it could get by crawling all my projects/notes/emails/slides/meetings/etc - This system should be designed to take action rather than simply just prioritizing messages. We've had prioritized inboxes for a long time but they're fine, not great - then someone has to put this entire UX together to be cohesive. In the future, we may not even really have an email inbox, but instead an interaction that feels more like I'm talking to an assistant who has a few questions for me. But otherwise just wants to provide a few quick updates and get some yes/nos. And otherwise filter all the noise -- just give me the most important messages It feels like we're very, very close to being able to do this, with the latest models from Anthropic and Open AI, we have the technology already. Someone just needs to package it all together in a way where it's able to index all of your emails and notes and calendars and contacts and sort of create a second brain that knows almost everything that you know so that I actually do things that are intelligent. It seems like with the excitement of OpenClaw we have the architecture to integrate a lot of different data sources and to take actions across multiple different channels. And it's built with one sort of monolithic memory and context, so that you're able to interact with it in such a way where it feels like it can try to replicate your actions more closely than the relatively stateless and memoryless LLM chats that we've gotten accustomed to. If someone is working on this, please point them to me. I would be both a customer and an investor!
2
3
43
8,270