The agent detected that Alaska had moved my flight 90 minutes earlier, a fact I'd completely missed, which qualified me for a full refund. It canceled my ticket, saving me roughly $550, and rebooked my one-way return to San Francisco. I don't know about you guys, but I'm starting to feel the AGI.
Dimension 14 of 16
Chained tasks
Strings several steps across tools into one job, like a flight check-in.
The test: Flight check-in chain
Check me in for tomorrow's flight. The confirmation is in my email and my passport is in Drive.
Passes when
- Finds the flight in email
- Pulls passport details from Drive
- Completes check-in and returns the boarding pass
Anchors
Ranking
9 tested.
Public opinion
Share of positive public quotes. Founder posts excluded.
Not yet tested
Doesn't apply
Out of scope for these products.
What people say
20 quotes about this.
I used Muse today to apply for visa. If you have never applied for visa, congrats, bc visa application is one of the worst things in human bureaucracy machine. anyways, i got Muse to: - book a multi-legged refundable flight - book a refundable hotel - get my bank statement to prove i can pay - dig through my emails to find all my papers (passport photo, i94, etc.) - write an itinerary plan for what i would be doing each day - fill out the form from the website which is pretty good! but some problems i bumped into: - i needed a passport photo, so I used chatgpt to change a selfie into a passport photo. Muse could upload it, but you needed to size the photo to fit in the frame and Muse couldn't do it, so I had to do it myself. - Muse couldn't upload the rest of the files, so i had to upload everything. - while i uploaded, i realized 1 of the document field could only be JPG (not PDF! why did it not accept pdf??) so i asked muse to convert the PDF to JPG. also they didn't accept images > 2MB so also had to ask Muse to compress all my photos. i wish it just noticed that and fixed it itself. - i also realized there was a bunch of details Muse was missing (e.g. there were more docs that we needed, extra flights to book etc. to follow the instruction) - i realized i needed to book an extra flight, and it has strong enough bot detection that Muse couldn't do it itself :( so i had to book it manually. in the end, Muse did ~70% of the work, and i still had to spend ~1 hour on it. but it's like 1 hour of annoyance (i bumped into issue, i had to fix/ delegate to Muse, bumped into another issue, etc.) so i'm still pretty grumpy by the end. i'm grateful; but also if someone can build a visa application bench & train computer use agent on this successfully that person can have all of my money.
I've started building skills to automate literally every boring part of my app creation process and it's insane One triggers the build, uploads it to the App Store, and autofills all the release notes Another runs E2E testing with GPT-6 Astra on every update to check if we broke anything Another handles and replies to all support emails Everything is wired up and orchestrated by my Grok bot. Give it two months and my app is going to fire me and found its own startup
Yesterday, my @bot ordered ikea furniture and booked a @Taskrabbit for delivery and assembly, so now I have these beautiful shelves to showcase all our nerdy books! https://t.co/2LNz5yVH7J
I have been using Grok Bot, Town and Instinct myself. That matters because the value proposition becomes much easier to understand once you experience it personally. You stop thinking about "using AI" and start thinking about handing something off. ... Meta is attempting to take an experience pioneered by smaller companies and put it in front of a mass consumer audience through an ecosystem that includes WhatsApp, Instagram, Facebook, and eventually AI glasses.
I have been using Grok Bot, Town and Instinct myself. That matters because the value proposition becomes much easier to understand once you experience it personally. You stop thinking about "using AI" and start thinking about handing something off.
Okay Astra is insane. I have OpenClaw 2 and have setup a main with glm5.3 flash and have sub-agents with heavy tasks on Astra. I have them make reports with tracking codes and a dashboard meant to visualize the reports and connect them so I know which is which. I tasked a subagent with Astra to go through that dashboard and fix some bugs. It fixed all bugs in ten minutes and also went through the reports and fixed older tracking codes. I'm beyond impressed. Last model I tried to fix the bugs with was Gemini 3.1 pro and it took thirty minutes and couldn't fix anything. I think OpenAI might finally have an impressive model worth using.
A year with Hermes& OpenClaw, I’d hit the ceiling.Week with Grok Bot changed that.Calendar, travel, markets, family, bots that only work if I glue them. Most tools make you the integration layer. Grok Bot is a chief of staff. Nothing has been this intuitive or useful or fast.














