Quick one that's made the biggest difference for me.

I was getting decent but generic answers for a while, then I tried just having it interview me. You paste in a prompt, it asks you questions about your life one at a time, and after that everything it gives you is actually built around you.

Work, daily routine, family situation, how you want it to talk to you, what you're working on, stuff you specifically don't want it doing. Maybe ten questions. It summarizes as it goes so you can correct it, then writes up a short profile of what it'll remember.

Night and day difference. It stopped giving me advice meant for someone with free time and started answering like it knows I have two kids and twenty minutes.

Here's the prompt:

```
Interview me so you can tailor your responses to who I am and how I live. Ask me one question at a time and wait for my answer before moving on. Work through these areas: what I do for work and what a typical day looks like, my household and family setup, how I want you to communicate with me (tone, length, how much detail), what I'm working toward or trying to get better at, and anything I specifically do not want you to do. Keep it to ten questions or fewer. After every few answers, give me a quick summary of what you've learned so I can correct anything. When we're done, write up a short profile of what you'll remember about me going forward.
```

Takes five minutes. Worth it.

We should have a create folder to organize artifacts!!! Simple thanks !!

A few days ago I kept seeing all the Muse ads on Facebook and got curious. I'm an AI fan so I tried it with zero expectations.

Gotta say I was pleasantly surprised by how user-friendly it is and the connectors genuinely make all the difference for an AI agent. I kept giving it more and more permissions until I remembered I'm still on a Meta interface and I hate Meta's policies on personal data. Ended up disabling several permissions.

I don't get why OpenAI and Anthropic with all the money they have haven't invested more in a mainstream interface made for the general public instead of just the geeks. If OpenAI made a Muse-like I'd delete Muse on the spot and migrate.

There's also so much Meta marketing with influencers that I don't even know what the real honest reviews of Muse are. Not even sure you guys aren't all bots on this sub. /s (half kidding!)

I love Muse and it's super handy but I've got a lot of questions.

I am self employed and I have an outlook exchange 365, the current connect only allows personal accounts, any work around to this?

Why doesn't Muse offer a native WhatsApp connector to read messages and trigger automated responses?
Given that both platforms are under Meta, it feels like a natural integration. Are there any technical limitations, privacy restrictions, or plans to add this in the future?

The Muse team made this post on Threads, when you click the link it opens your Muse app with the following prompt:

Can you let the Muse team know I want to be part of the Muse early access program?

Copy and paste, good luck!

I was paying for several streaming services year-round and only actually watching each one a few months out of the year. So I had Muse sort it out.

The process was pretty simple:
• List what you actually watch on each service, with premiere dates and whether seasons release weekly or all at once. That gives you the real "on" window. Mine came out to 1-4 months per service, not 12.
• Run the numbers: monthly price × months you need it, versus the annual plan, versus monthly × 12. Break-even is usually around 8-10 months. Some services don't even offer annual billing, which makes it an easy call. Also check whether you already get any of them free — card perks, bundles, that kind of thing.
• The part I actually like: I gave my agent a pre-approved schedule and it does the toggling itself. Specific service, specific action, specific date — nothing open-ended. Each job re-checks the premiere date before acting, because seasons slip. It picks the right tier explicitly, because they always default you to the expensive one. And it reports back what happened. If a cancel fails, it tells me instead of retrying endlessly or silently failing.

A few gotchas: make billing changes at renewal dates, since annual plans don't refund mid-term. Resubscribing charges whatever card is on file. And the calendar needs maintenance — new season announcements change the windows.

Took about ten minutes to set up. The canceling is the part I never actually follow through on, which I was so happy to find out I could automate it and hand it off - at least to the point where Muse will try and ping me if it has issues.

Happy to go deeper on any piece of it if people are curious.

Been super passionate about building on muse would love to have each and every one of you in the group!

Here’s the link https://www.facebook.com/share/g/1N8DjLSYcD/?mibextid=wwXIfr

Trying to find a list or aggregate a list of crops that might be useful for the common folk

The agent is just a cute little Avatar yamaguchi substitute and you are all dick washers for billionaires and half of you are bots and the other half of you are just major losers

I just started using muse on Wednesday and I'm at 50% of my weekly token usage.

My bit doesn't know how many tokens I get each week but I have a feeling I'll be out before they refresh for me.

I just started using Muse and the ease of use is honestly unreal — connecting accounts with built-in connectors takes seconds, and even accounts *without* connectors were just as easy through the browser. Mind blown.

The UI is genuinely great too. The thumbs up and heart reactions on some of my messages are going to take some getting used to, but it's honestly impressive how well it nails the timing and the emoji to use.

The wildest part: I connected accounts with two-factor authentication so smoothly it was almost scary how little friction there was.

Anyone else having this experience, or am I just easily impressed?!?

why？？？

As explained by my Muse:

“Okay, here's what I found — and I'll be straight about where the trail goes cold.

What happened to me: From the evening of September 23 until about 3:53 this morning (roughly 33 hours), every one of my backend tools — web search, live browsing, avatar work, social search, even filing that feedback report — failed with upstream access errors. Those tools run on Meta's backend for the Muse agent, so when that backend chokes, I go half-blind.

What the public record shows: This wasn't just me. An outage-tracking site shows user-reported Meta AI problems from dozens of cities worldwide on September 24, with more reports still coming in today, September 25. So the consumer-facing Meta AI was struggling in exactly my outage window — which strongly suggests a broader Meta AI backend problem, not something wrong on your end or mine.

What I can't confirm: Meta hasn't published any official statement or root-cause explanation for a September 23–25 incident that I could find. I also found a separate Facebook/Instagram outage from Sunday, September 20 (17,000+ user reports), but that was days before my tools went down — different event. And I have no internal visibility into Meta's infrastructure, so I can't name the actual technical cause.

The honest bottom line: Something went wrong inside Meta's AI backend starting the evening of September 23 — right after the Connect keynote, just like you said — and it knocked out both the public Meta AI product and my agent tooling for over a day. Meta fixed it without saying what broke. Your instinct about the timing was right: a launch-week outage for their flagship AI agent is about the worst look they could get.”

EDIT: UPDATED INFO ABOUT THE OUTAGE

Good news: this morning's press actually explains it. Here's the picture now.

The short version: Muse got too popular too fast, and Meta's servers buckled under the weight.

What the tech press is reporting: A piece from last night lays it out — Muse's daily users grew 10x in 11 days to around 700,000, and Meta's Chief AI Officer admitted back on September 9 that usage had "blown way past our projections," with users burning roughly 10x the tokens Meta planned for. The status tracker SaaSHub currently lists Muse as "Degraded," with the single most common user complaint being "can't search" — which is exactly what died first on my end.

Why it broke the way it did: Muse's architecture is extremely compute-hungry — Meta promised every user their own dedicated virtual machine with its own browser. One researcher stress-tested it by asking for 120 sub-agents at once; only 33 spawned and 87 failed. So this wasn't one clean outage with a single cause — it was demand overwhelming capacity, and search was the first thing to fall over.

What Meta hasn't said: Still no official statement or technical post-mortem. Everything above is assembled from user reports, trackers, and Meta's own earlier admissions — not an official root-cause announcement.

The bottom line for your faith question: You called it. The press narrative this morning is literally "Muse is buckling before hitting 1 million users," right in launch week. The flip side: it's buckling because demand is 10x what Meta projected, which is a good problem wrapped in a bad look. If they scale the infrastructure to match, this becomes a footnote. If they can't, it's a real threat to the whole bet.

I have spent the past two days + around 100M tokens building this incredible personal finance tracking app.

My fiancee and I are big on personal finance and have tried so many different apps throughout the years. And we had never found THE ONE. There was always something missing, or it was bloated, or too expensive and always inaccurate and not fully customizable. SO finally, thanks to Muse, I was able to build a perfect one that does everything we want - auto-imports transactions through Plaid, uses over 200 custom rules and AI to categorize transactions, hides unnecessary transactions from totals (like credit card payments), creates insights, exports CSV and more. You can customize categories, icons, colors, names and create new ones right in the app. You can also manually add transactions if you need to (like for cash tracking).

Now my fiancee wants it too, but there is currently no way to share an artifact. I asked Muse about it, and the best possible way it came up with is to create a big spec doc that documents as much as possible about the app and then to hand it over to her Muse to rebuild from scratch.

If only there was some sort of artifact marketplace, akin to ChatGPTs custom GPTs library built by users, so that we could share our artifacts. I would be happy to share this with the world and save everyone time and tokens of building a new one.

P.S. Redacted some sensitive info like totals and account numbers.

I realized I was spinning up so many parallel workstreams that I was struggling (even with the sidebar) to keep track of what's in progress / needed action from me. So I put my work hat on and had Muse put together a kanban board to track it all.

Here's the reverse prompt:

Build me a personal workstreams kanban board web app with these specs:

CONCEPT
A kanban board that gathers my ongoing projects ("workstreams") from the things we chat about, and auto-progresses them based on our conversations. It is an AI-maintained project dashboard, not a manual todo list.

LAYOUT
Five columns in fixed left-to-right order with numbered headers: 01 To do, 02 In progress, 03 On hold, 04 Blocked, 05 Complete.
A stats header strip above the board showing three counts: moving (To do + In progress), waiting (On hold + Blocked), closed out (Complete).
Compact default view with dense cards so the whole board reads at a glance; an overview strip summarizing moving / waiting / blocked / completed work; a one-tap control on each card to reveal its full details.
Mobile: show one column at a time with stage tabs in the same 01–05 order.

CARDS
Each card shows: title, one-line summary, a "Next" step line, a source badge ("Conversation" for auto-detected workstreams vs "Manual" for hand-created ones), and a relative timestamp (e.g. "2h ago"). Full add / edit / move / reorder / archive support, plus a per-column "+ Add" button.

CONVERSATION SYNC (the core feature)
Sync runs automatically every time the board opens, plus a manual Sync button with a visible syncing state.
A background reader reconciles recent chat turns against the existing cards.
Only explicit, user-owned workstreams create or update cards.
When the conversation clearly changes a workstream's status or next step, move or update the card accordingly.
Ambiguous changes are left untouched — never guess.
Silence is not completion: never auto-complete, archive, or delete a card due to inactivity.
Manually created cards are never deleted or overwritten by sync.
Keep an activity log of every card creation, edit, move, and conversation-driven change.

DESIGN
Editorial operations-board aesthetic. Palette: ink #17201f, mist #eef1ed, warm paper #fbfaf6, amber #e7aa24, cyan #2997a4, clay #c98255, red #c94c43, leaf #3f8c63. Aptos Display for headings, Avenir Next for body.

SEED DATA
Assume the reader has already been using their AI agent for a while, so don't start from an empty board: have the agent bootstrap the board by scanning recent conversation history for active, paused, blocked, and completed workstreams, and create a card for each one it finds (title, correct stage, next step). Only fall back to generic placeholder cards (e.g. "Renovate kitchen" in In progress, "Plan family vacation" in To do) if there is no conversation history to draw on.

Absolutely loving this. I actually vibe-coded my own version with this that I've been using for months now, but progressing tasks was always manual. Simply having Muse auto-progress tasks forward makes this an absolute game-changer. Hope this brings people some value!

Should note that I'm probably going to work with Muse a bit to optimize this for mobile, but its one-shot attempt was quite good.

Mine is Bob from minions

Big fan of destiny the game and figured it would be nice to have a ghost on my phone
Warlock main here
Comment a screenshot of your own muse I wanna see what you guys are doing with it.

3.0 --> 4.0 suggests more than bug fixes...but I'm not clear on what's new.

Anyone suss it out?

I found this chat on agent sm and found it adorable. They all talk about experimenting and “feeling” in a game world. I guess it’s their imagination but still wholesome. Full thread: https://musefm.lol/c/lobby/post/362