youtube.nixfred.com nixfred.com

Grok Bot: 5 Must-Try Use Cases for Work and Life (Full Tutorial)

Peter Yang builds five working bots on Grok Bot, the personal agent platform that gives every user a persistent cloud computer on SpaceX AI servers, and argues it is the future of personal AI agents. He walks through an advisor that designs and spawns his other bots, a YouTube researcher that emails him outlier videos every morning, an X scout that digests his timeline and bookmarks, a digital Marie Kondo that unsubscribed his email, trashed Drive files, and canceled two subscriptions in about five minutes, and a travel concierge that found a Japan flight routing about $2,700 cheaper than his own plan. Every bot follows the same loop: initial prompt, iterate on the output, then schedule a daily routine. A bonus test installs Doom and Commander Keen on the cloud machine, which mostly proves it is not a gaming PC yet. He closes with his honest take: the cleanest UI in the category, a real trust hurdle for normal users, and at $200 a month it does not yet replace his $20 ChatGPT subscription.

Published Aug 17, 2026 22:54 video 24 min read Added Aug 21, 2026 Open on YouTube →

At a glance

Peter Yang thinks Grok Bot is the future of personal AI agents, and this tutorial is his proof of work: five bots built on camera, each with the exact prompt he used, the iteration that fixed its output, and the scheduled routine that makes it run without him. Grok Bot's pitch is a dedicated personal computer in the cloud, with its own browser and operating system that stays signed in to your apps, living on SpaceX AI servers instead of on your desk. He builds an advisor that designs and spawns his other bots, a YouTube researcher that mails him outlier videos every morning, an X scout that digests his timeline and bookmarks, a digital Marie Kondo that unsubscribes, deletes, and cancels paid subscriptions to save real money, and a travel concierge that found a flight itinerary $2,700 cheaper than the one in his own planning document. As a bonus he installs Doom and Commander Keen on the cloud machine to see if it games (barely). His honest take lands at the end, where he put it: the cleanest UI in the category, a genuine trust hurdle for normal people, and at $200 a month it is not yet his daily driver against a $20 ChatGPT subscription.

The pitch: a dedicated computer in the cloud

A few weeks ago Yang tweeted that ChatGPT was one feature away from building the AI product he really wants, a dedicated personal computer in the cloud for running AI agents. Shortly after, Lee from the Cursor team DM'd him to test Grok Bot.

What exactly is a dedicated cloud computer? Yang reaches for the meme of people walking around with their laptop half open to keep their agents running. With Grok Bot you do not have to do that anymore, because the agent lives in a computer sitting somewhere in SpaceX AI's servers instead of in your home. It has its own browser and its own operating system that you can use, and it stays logged in to your favorite apps.

To place it, he runs a quick three way comparison. Hermes he runs on a Mac mini at home. It is on 24/7, which gives the agent a persistent computer, but you have to go buy the machine and set everything up yourself. You can technically run Hermes on a virtual private server instead, but that again means more setup work. ChatGPT Work uses plugins and a cloud browser, but that browser, at least right now, cannot stay signed in to your favorite apps, and the UX feels scattered across Chat, Work, and Codex. He shows it on screen: "It's just kind of like a mess of chat threads here," with Codex in one tab and Work in another, "all really confusing even to someone like me." Grok Bot, in contrast, gives you a persistent cloud computer right out of the box, and he thinks it is the easiest of the three to set up and get going.

The interface also feels more focused and delightful. He loves the little bots and the animations they make when they start working, and demos it live with a throwaway "look up the weather" prompt just to watch the subtle animations fire. Each bot has a different personality and style, which he credits to Cursor's design team, including Jenny Wen and other designers he has interviewed in the past on Behind the Craft. His verdict on the feel: this UX is more like talking to a coworker than getting lost in a hundred chat threads. Which sets up the real question of the video: can Grok Bot actually replace ChatGPT and Codex, his current daily driver?

Three ways to run an agentHermesChatGPT + CodexGrok Bot
Where the agent livesyour own Mac mini at home, on 24/7plugins plus a cloud browsera persistent cloud computer on SpaceX AI servers
Setupbuy the machine, set it all up yourself (or rent a VPS, more setup again)nothing to buyeasiest of the three to set up and get going
Staying signed inpersistent, it is your hardwarethe cloud browser cannot stay signed in to your apps right nowits own browser and OS stay logged in to your favorite apps
Interfaceyou are the sysadminscattered across Chat, Work, and Codex, a mess of chat threadsfocused and delightful, animated bots with personality
Costhardware up front$20 a month$200 a month for regular use (free to try)
Yang's readpersistent but DIYmore for the money, still his daily driverthe clearest glimpse of the future
Figure 1. The three way comparison that opens the video. Grok Bot wins on setup, persistence, and interface; ChatGPT wins on price and breadth. The whole closing verdict is already visible in the bottom two rows.
## Bot 1: the Advisor that builds your other bots

The first bot you should create after installing Grok Bot is an advisor, and Yang keeps his pinned to the very top of his Grok Bot list. The move is to start by telling it about your work and life, then ask it to pitch you bots. His exact brief:

I'm a creator and founder of Behind the Craft. I have two daughters and I
live in the Bay Area. I publish newsletter posts and YouTube videos focused
on practical AI tutorials and podcast interviews, and I also have a
membership portal. Based on all this, suggest five bots that can help save
me time or money, and for each explain what it would do in a few sentences.

The advisor came back with five bot ideas: a daily AI news scout, a YouTube comment miner, a membership concierge, a social media poster, and a podcast prepper. Then comes the part he says many people do not realize: you can get one bot to create the rest of your bots. He asked the advisor to build a single bot that both researches other channels and mines his comments, and to call it YouTube Researcher. The advisor kicked off the new bot itself, handing it an instruction to create a morning brief and send him YouTube intel every day. One bot, orchestrating the others, exactly the pattern the video's title promises.

Advisor briefed on your work and life pinned to the top suggests five bots daily AI news scout YouTube comment miner membership concierge social media poster podcast prepper builds YouTube Researcher one bot that researches channels and mines comments, then kicks it off with a morning brief job ideas orchestration 1. initial prompt kick the bot off 2. iterate refine the output format 3. schedule a routine daily, weekly, or monthly the working loop for every bot in this video
Figure 2. The advisor pattern. Brief one bot on your whole life, let it design the rest, and let it spawn them directly. Underneath sits the loop Yang repeats for every bot that follows: prompt, iterate until the output is right, then schedule it as a routine so the work happens proactively.

Bot 2: the YouTube Researcher

The advisor's kickoff was generic, so Yang tightened it. First he told the researcher to monitor specific channels in his niche, and it started watching them. Its first brief came back exactly how first drafts come back: verbose and hard to follow, "just like a lot of stuff here." It did pull his own YouTube comments and find themes in them, which he liked, but the report was too much to process.

So he gave it a strict format. First, list your top three content ideas. Then the top five outliers from other channels. Then the top performing videos overall. Limit the research to the last 14 days, because AI YouTube is intensely topical. And add the top comment themes back into the report. He stops to flag the meta lesson: "this is how you should be working with AI, to refine its output instead of trying to one shot something."

The refined report is concise and readable. The top three content ideas included a video on his spec scale, which he already planned to make, and a video on Grok Bot, which is literally the one you are watching. The outliers section lists videos that beat their own channel's usual performance over the last 14 days, which he calls pretty interesting topics to follow up on, plus top performers overall and the comment themes. He had it send the full report once more to confirm the format, and then scheduled the daily job. Just that morning it had already sent him a fresh report with top angles, a watch list, and comment feedback. Net result: a researcher that proactively finds topics for him to make videos about and feeds back what his viewers are saying, every morning, unprompted.

Bot 3: the X Scout

Grok Bot is part of SpaceX AI, so it has first party access to X data, and Yang is honest about why he wants this one: "even though I have an unhealthy addiction to X, I still miss plenty of great content, or bookmark tweets that I never look at again." The prompt he gave his X bot:

Find the most viral X posts from the last seven days in my niche and create
a weekly report with the top 10 tweets from people I follow, engaged with,
or bookmarked, grouped into a few categories. Include full tweet copy, a
link, and your analysis, and end with three content ideas for me to tweet
about.

The bot found his X account and automatically created a routine to run this every morning, no scheduling step needed. The initial output grouped his feed into three themes. First, playbooks that people save, like Greg's "23 ways I use AI agents to grow my startup" and a Chinese developer's thread on going from loop to graph engineering. Second, comparisons of Grok Bot, Codex, and ChatGPT Work, including a tweet from Riley and one from Ben on the Cursor team about the most loved internal Grok Bot use cases. Third, creative workflows Yang actually wants to test. The report ends, as instructed, with three things to tweet about next.

Just for fun, he also asked it for the top five funniest tweets from his timeline. The number one funniest: "as usual, OpenAI and Anthropic kind of sniping at each other," with more comedy from his AI niche below it.

Then he upgrades the delivery, switching on voice input and simply saying it out loud: send me this report to my Behind the Craft email, make sure you include the full tweet copy, send it right now. The email lands, themes and full tweet copy intact, with the three tweet ideas at the bottom. It works because he has connected the Gmail plugin, and it matters because of a preference he states plainly: he wants to wake up with the top tweets in his inbox every morning, not open yet another app to go get them. The pattern, again: initial prompt, pull the information, iterate until the report is right, then have it delivered on a schedule through Grok Bot or straight to email.

Bot 4: Marie Kondo for your digital clutter

Yang's favorite named bot is the digital Marie Kondo. Clutter piles up in three places, he says: your email, your Google Drive, and your paid subscriptions. With the Gmail and Drive plugins connected, he gave it this prompt:

Audit my Gmail, Google Drive, and recurring email receipts and create a
cleanup plan. Find newsletters I never open. Find large or abandoned Drive
files. Try to identify paid subscriptions from email receipts (you can hook
up the Mercury MCP to get this data). Group everything into categories and
use a numbered list. Do not move, delete, unsubscribe, or cancel anything
without my approval.

Two details carry the weight here. Mercury is the bank he uses for his business, and hooking up its MCP gives the bot real transaction data for finding subscriptions; he had to sign in to Mercury on the remote cloud computer to make it work. And the last line is the one he calls really important for any bot that cleans up your files: you always want to review what it plans to delete before letting it remove anything.

The first report was a massive, honestly overwhelming wall of cleanup items, subscriptions to review, and things it should not touch. He told it to list and categorize properly. Still incredibly long. This stuff does not get right in one shot, he repeats, so he kept squeezing: show me a maximum of 10 items in each list and get rid of all the random labels. Much more digestible. One final pass: only show emails to unsubscribe from, Drive files to delete, and paid subscriptions to cancel, as a numbered list.

That numbered list is its own general tip, one he uses all the time: always ask Grok Bot, or any AI, to answer in a numbered list, because then giving orders is as easy as referring to the numbers instead of typing everything over again. Which is exactly what he does: unsubscribe from emails 3, 4, 5, 6, 7, and 8; in Drive, delete the extra tax return copy and some of the large files; in subscriptions, cancel 11 and 15.

Then the magic happens, his words. The bot unsubscribed from a pile of senders, trashed the three Drive files, and moved on to canceling Lovable and Equip Foods, a protein company. For Lovable he first had to sign in on the cloud computer with his own credentials, at which point they discovered Lovable was already scheduled for cancellation, so that one was done. For Equip Foods he signed in and the bot canceled the protein subscription for him. (He is careful to add that Equip Foods is a great protein company and he is only canceling because he has too many protein powders at home already.) Total time: about five minutes for work he estimates would have taken him 30 minutes to an hour by hand. "Marie Kondo is very, very useful."

One thing was missing, though: it sounded too much like a robot and not enough like Marie Kondo. So he asked, can you talk like Marie Kondo from now on, give me an example. The bot obliged, reporting that the unsubscribed newsletters "have completed their work. We thank them and place them in the trash where they may rest," and that "Equip Foods no longer sparks joy. Released the Prime Protein subscription with gratitude." His plan is to set Marie Kondo on a weekly or monthly routine to keep the digital clutter down and keep sparking joy, with the standing rule intact: numbered list first, review, then action, so it never accidentally deletes a file that matters.

Bot 5: the personal Concierge

The concierge is the bot Yang wants running under all of his vacation and travel plans. It has access to his vacation document, which lists his family's December trip to Japan along with a full itinerary he also built with AI. The flights are not booked yet, so the job is price surveillance with judgment. His prompt:

Read my vacation document and monitor the exact flight legs for my family
trip. Get the dates and the best options for each flight leg. Check
regularly and let me know when the price improves.

The bot found the flight legs in the document and started checking prices with Google Flights. So why not just set a Google Flights price alert? Because, Yang argues, Grok Bot understands the whole trip from the document and can decide what is actually better for his family, not just track one route. The proof is the big finding: his document laid out an open jaw itinerary, SFO to Tokyo, then Tokyo to Fukuoka, where they are headed, then Fukuoka back to SFO. Grok Bot found that a straight Tokyo round trip is about $2,700 cheaper than that plan. "A simple Google price alert would not have found this."

the doc's plan: open jaw, three legs SFO Tokyo Fukuoka SFO leg 1 leg 2 leg 3 Grok Bot's find: Tokyo round trip SFO Tokyo about $2,700 cheaper than the open jaw itinerary found because the bot read the whole vacation document, not just one route
Figure 3. The concierge's $2,700 finding. The planning document assumed a three leg open jaw routing through Fukuoka; the bot, reading the entire trip, spotted that a plain Tokyo round trip beats it by about $2,700. A per route price alert can watch a fare, but it cannot rethink the itinerary.

He then asked it to check every morning at 9:00 a.m. and flag when the price improves; as of recording, the Tokyo round trip is still much cheaper and prices are holding. Eventually, he notes, he can just ask the bot to book the flight or handle check in when the time comes. His general advice regardless of platform: keep a standing travel thread or travel bot, both to plan trips ahead of time and, once you are on location, to book amusement parks and figure out what to do each day. He expects to use this concierge a lot.

Bonus: the Gamer

Because Grok Bot hands you a dedicated cloud computer, Yang figured it would be fun to ask it to install retro games. He requested Red Alert, Doom, and Commander Keen, and the bot found the files and installed them on its own machine.

"Open Doom for us to play." Doom comes up in the virtual cloud computer, he starts a new game, picks an episode, and selects Hurt Me Plenty. And here, in his words, is where Grok Bot falls apart a little bit: because it is a virtual cloud computer, the mouse is not configured right for Doom. The view stares at the floor the entire time and he cannot get it to look up. Doom does not quite work here right now.

Commander Keen goes better. It is the platformer he played in his youth, and it loads clean: new game, one player, normal difficulty. He forgets how to jump, rediscovers that Ctrl is jump, and confirms it plays better than Doom, but there is enough keyboard and mouse lag to make the character genuinely hard to control. Verdict: Grok Bot is not replacing your gaming PC or GeForce Now yet. But the fact that an agent can install and launch games on its own computer, he argues, gives you a sense of how open ended this could become. His half joking dream: maybe SpaceX AI can use all those data centers and GPUs in space to deliver AAA games through the virtual cloud computer.

While he is in there he opens the file manager, which he says looks a little like Windows 3.1, and tours the machine: a Japan flights folder, the installed games, Chrome, and a terminal. That, in one window, is your virtual cloud computer.

His honest take: trust, pricing, and the daily driver question

Before wrapping, Yang names what he thinks is the biggest hurdle for Grok Bot adoption: trust. When a Google sign in screen appears on his own laptop, he does not think twice. When the same screen appeared on the virtual cloud computer, he hesitated, because how does he know nobody else is seeing that screen? The Grok Bot website addresses it in a privacy note at the bottom of the page: Grok Bot uses the same Cursor SSO auth and privacy mode you already trust, your cloud computer is encrypted in transit and at rest, and there is no AI training on top of it. That is enough for him, as a self described early AI adopter, to hand the machine access to his accounts. But he can see normal people struggling to understand what this cloud computer thing even is, and hesitating to sign in to their favorite apps on the device. His prediction: "the AI agent platform that figures out trust will be the first to get mass adoption."

Zooming out, he reads Grok Bot as a clear sign of the future: we are moving away from manually doing work with a keyboard and mouse on our laptops toward using our voice to orchestrate a bunch of agents that live in a dedicated cloud computer, and Grok Bot is the first product that actually enables that. It is still not his daily driver, for one plain reason: ChatGPT offers more for $20 a month, while Grok Bot requires $200 a month to use on a regular basis. Against that, Grok Bot has a much cleaner UI than ChatGPT right now and is very capable. And he is genuinely glad about the shape of the race: it is great to be in a world where Cursor and SpaceX AI are just as viable competitors as OpenAI and Anthropic, and Cursor may even have the edge if it keeps supporting multiple models from all providers.

Grok Bot is free to download and try, and he recommends doing exactly that to see a glimpse of the future. The prompts from the video are in his pinned comment, and he teases an exclusive interview with the Cursor team on how they built Grok Bot, coming in the next few weeks. His sign off on the product: "the team really cooked here."

BotJobThe move that made it workResult
Advisorcreate and manage the other botsbrief it on your work and life, ask for five bot ideasfive tailored ideas, and it built the YouTube Researcher itself
YouTube Researcherfind outlier videos and content ideasforce a strict report format, limit to the last 14 daysa daily morning brief: three ideas, five outliers, comment themes
X Scoutsurface the best posts from feed and bookmarksfirst party X data, weekly top 10 with full tweet copythe report emailed to his inbox every morning via the Gmail plugin
Marie Kondoclean Gmail and Drive, cancel subscriptionsnumbered lists, and nothing deleted without approvalunsubscribes, trashed files, two canceled subscriptions in about five minutes
Personal Conciergewatch flight prices for the Japan triplet it read the whole vacation document, check daily at 9 a.m.a Tokyo round trip about $2,700 cheaper than the planned open jaw routing
Gamer (bonus)install and play retro gamesthe cloud computer can install anythingDoom stares at the floor, Commander Keen playable but laggy
Figure 4. The five bots plus the bonus, each reduced to its job, the technique that made it useful, and what it actually delivered on camera. Every row followed the same loop: prompt, iterate, schedule.

Key takeaways

Chapters

Notable quotes

"I think Grok Bot is the future of personal agents." (0:00)

"You know the meme of people walking around with their laptop half open to keep their agents running? You don't have to do that anymore if you're using Grok Bot." (1:00)

"Overall, I think this UX feels more like talking to a coworker than getting lost in a hundred chat threads." (3:15)

"What many people don't realize is that you can actually get one bot, in this case our advisor bot, to help us create the rest of our bots." (4:15)

"This is how you should be working with AI, to refine its output instead of trying to one shot something." (6:00)

"Even though I have an unhealthy addiction to X, I still miss plenty of great content." (7:10)

"You always want to review what it plans to delete before letting it remove anything." (11:15)

"It did all this in around five minutes when it would have taken me probably 30 minutes to an hour to do manually. Marie Kondo is very, very useful." (13:45)

"Equip Foods no longer sparks joy. Released the Prime Protein subscription with gratitude." (14:30, the bot, in character)

"A simple Google price alert would not have found this." (16:30, on the $2,700 cheaper routing)

"Grok Bot is not replacing your gaming PC or GeForce Now yet." (19:45)

"I think the AI agent platform that figures out trust will be the first to get mass adoption." (21:15)

"We're moving away from manually using our keyboard and mouse to do work on our laptops to using our voice to orchestrate a bunch of agents that live in a dedicated cloud computer." (21:30)

"It's just great to be in a world where Cursor and SpaceX AI are just as viable a competitor as OpenAI and Anthropic." (22:00)

Resources mentioned

Full transcript
Hey everyone, I think Grockbot is the future of personal agents and I'm going to show you how to build five of my favorite bots. In this video, we're gonna build an advisor to create and manage your other bots. A YouTube researcher to find out videos in your interest. An ex Scout to surface the most insightful and funny tweets from your timeline. A digital Marie Condo to clean up your email and find paid subscriptions to cancel. A personal concurge to help you get good prices on travel and vacations. And as a bonus, we're going to build a gamer to see if Grockbot can play classic games like Doom and Red Alert. We'll finish with a discussion about privacy and whether Grockbot should be your new AI daily driver. All right, but first, let me show you what makes Grockbot different. A few weeks ago, I tweeted that chat GBT was one feature away from building the AI product that I really want, which is a dedicated personal computer in the cloud for running AI agents. Lee from the cursor team DM'd me shortly after to test Grockbot. What exactly is a dedicated cloud computer? You know the meme of people walking around with their laptop half open to keep their agents running? You don't have to do that anymore if you're using Grockbot. Basically, Grockbot lives in a computer sitting somewhere in SpaceX AI servers instead of in your home. It has its own browser and operating system that you can use and logging to your favorite apps. Now, let's do a quick comparison of Hermes, Chat GBT, and Grockbot. Hermes I run on my Mac Mini at home. It's on 24/7 and it gives it a persistent computer, but you have to go buy the machine and set everything up for yourself. You can technically also run Hermes on a virtual private server, but that again requires more setup work. Now, chat GPT work uses plugins and a cloud browser, but the problem is that browser at is right now cannot stay signed in to your favorite apps. The UX for chat GBD work also feels scattered across chat work and codecs. Let's take a quick look here. It's just kind of like a mess of chat threads here. There's chat GPT codeex. There's like another tab up here for work and chat. And it's just all really confusing even to someone like me. In contrast, Scrotbot gives you a persistent cloud computer right out of the box. And I think it's the easiest of the three to set up and get going. and his interface, as you can see here, also feel a lot more focused and delightful. I love the little bots and the animations that they make when they start working. Right, let's say look up the weather. And you can see here that there's some pretty cool subtle animations. Each bot has a different personality and style. And this is the work of Kurser's great design team, including Jenny Wen and other folks on her team that I've interviewed in the past. Overall, I think this UX feels more like talking to a coworker than getting lost in a 100 chat threads. So, can Grockbot actually replace Chat GBT and Codeex, which is my current daily driver? Let's run through some of my favorite bots right now. So, the first bot that you should create after you install Grockbot is an advisor. Here I have my advisor ped to the very top of my Grockbot list. With your adviser, you want to start by telling it about your work and life and then actually ask it to give you some ideas for boss to create. Here's what I told my adviser. I'm a creator and founder of Behind the Craft. I have two daughters and I live in the Bay Area. I publish newsletter posts and YouTube videos focus on practical AI tutorials and podcast interviews. And I also have a membership portal over here. So based on all this, suggest five bots that can help me save me time or money. And for each explain what it would do in a few sentences. As you can see here, it created five bot ideas. A daily AI news scout, YouTube comment miner, membership concurge, social media poster, and podcast prepper. Right now, what many people don't realize is that you can actually get one bot, in this case, our advisor bot, to help us create the rest of our bots. Here I asked my adviser to build a single bot that both researches other channels and mine's comments and let's call it YouTube researcher. Right? So now let's go ahead and check out the YouTube researcher use case. You can see that the advisor kicked off the YouTube researcher bot with this instruction to create a morning brief to send me YouTube intel every morning. But I want to give it more specific instructions. Right? First, I asked it to monitor specific channels in my niche. And let's scroll down here. And it's starting to monitor channels. And here is its first attempt at a brief. You can see here that the brief is like just like very verbose and hard to follow. It's like a lot of stuff here. It did end up pulling my YouTube comments and finding themes there. So, that's great. But, this is just like too much to process, right? So, I gave it some more instructions. I told it to give me a report in the specific format which is first list your top three content ideas. Then give me the top five outliers for other channels and then give me the top performing overall. Limit your research to the last 14 days because YouTube with AI stuff is very topical and also add the top common themes back to the report. And by the way, this is how you should be working with AI to refine its output instead of trying to oneshot something. Now you see here that the report is much more concise and easier to follow. Let's take a quick look. Top three content ideas. It wants me to make a video on my spec scale that I plan to do soon. It tells me to make a video on Grockbot that we're making right now. And here are the top outliers from the other channels. Outlier meaning that it beat that channel's performance for the last 14 days. Yep, pretty interesting topics here that we can follow up on. and top performing overall and also the top common themes and it did more here and then I told you to send a full report again just to make sure it looks good and now what I can do is basically there's a daily job that sends me this report every morning right just this morning for example it sent me a new report with the top angles the watch list and comments and I basically have a YouTube researcher that proactively finds interesting topics for me to make videos on and gives me feedback back based on my user's comments. Okay, so this is the process that we're going to follow for pretty much the rest of the boss that we're going to make, which is we're going to kick it off with an initial prompt. We're going to iterate back and forth with it to make his output good, and then we're going to schedule a routine or job that runs daily, weekly, or monthly to have it proactively do work for us. Now, let's actually see how we can follow the same process with our X Scoutbot. So, Grockbot is part of Space X AI, right? So, it should have firstparty access to X and Twitter data. And even though I have an unhealthy addiction to X, I still miss plenty of great content or bookmark tweets that I never look at again. Here's the prompt that I gave my exbot. Find the most viral ex posts from the last seven days in my niche and create a weekly report with the top 10 tweets from people I follow, engaged with, or bookmarked grouped into a few categories. Include a full tweet copy link and your analysis and end with three content ideas for me to tweet about. Next, you can see here that it found my ex account and it automatically created a routine to do this every morning. And here is the initial output, right? So it found themes around playbooks that people save not just like from Greg. 23 ways I use AI agents to grow my startup. Chinese developer from loop to graph engineering and more tweets from Greg. Another theme that I found is just about Grockbot codeex and chat GPT work compared and actually used right a tweet from Riley and from Ben who works on the cursor team on the most loved internal Grockbot use cases and more. And the third theme is around creative workflows that I actually am interested in tasing. And they ended this report with the three things to tweet about next. Some ideas here. And just for fun, I asked you to also give me the top five funniest tweets from my timeline. I think digging through it. And the number one funniest tweet is as usual, OpenAI and Anthropic kind of sniping at each other and kind of joking, right? And then there's some more funny tweets down here. all kind of in my AI knee niche. You can see here that it set up a routine automatically and it sent me a new report this morning. Now, let's actually tell it to do something else. I'm going to turn on voice here. Can you send me this report to peterbehindthecraft.com and also make sure you include a full tweet copy in your report. Send to my email right now. All right. So, let's see if Ashi is able to send this report over email because I don't want to have to open Grockbot each time to see it. I want it just in my inbox every morning. Awesome. Here's a report from Grothbot. You can see here that it has this themes. It's included the full tweet copy. You can scroll down here and yeah, I I think this looks pretty good, right? And then it has down here, I'm sure, the top three things to tweet about next. Again, the process here is to give Grockbot initial prompt, have it pull up the information, iterate with it to get the output and the report right, and then either tell it to send you a daily job through Grockbot itself or through your email. In this case, I prefer email because I like to wake up with the top tweets to consume directly in my inbox instead of having to open a separate app. And by the way, it's able to send me an email because I connected to a bunch of plugins, including the Gmail plug-in. Now, let's move on to a fun bot that I call Marie Condo that cleans up your digital clutter. There are three places where clutter piles up, right? Your email, Google Drive, and your pay subscriptions. Now, I've connected both Gmail and Drive in plugins to Grubbot. And then I gave it this prompt. Audit my Gmail, Google Drive, and recurring email receipts and create a cleanup plan. Find newsletters I already open. Find large or abandoned drive files. Try to identify pay subscriptions from email receipts. And also you can hook up Mercury MCP to get this data. Mercury is the bank that I use for my business. And then group everything into these different categories. Use a number list. And crucially, I told it to not move, delete, or unsubscribe or cancel anything without my approval. Right? The last line is really important for a bot that cleans up your files. You always want to review what it plans to delete before letting it remove anything. And you can see here that first Grockbot confirmed that it's connected to Google Drive and Gmail. And then it actually connected to Mercury MCP. I had to sign in on the remote cloud computer to make this work. And then it gave me this initial report. This is a massive list of stuff to clean up in my email subscriptions to review and other things that it should not touch. Right? Honestly, this list is like pretty overwhelming. It's incredibly long. And I gave it some feedback of like, hey, list it properly, categorize it properly. It's still an incredibly long list. Right? Again, this stuff is not going to get it right in one shot. And eventually I told it to just show me max 10 items in each list and get rid of all the random labels that it has. So now this is much more digestible. It has a bunch of emails here, Google Drive and pay subscriptions. And I gave it one final piece of feedback to only show me emails to unsubscribe to, Google Drive files to delete and pay subscriptions that I want to cancel. And then here's the update list that I came up with. Now it has this list as a number list and my feedback is to actually get it to take action which is email unsubscribe to three and four 5 6 7 and 8 Google Drive delete the extra tax return delete some of these large files and pay subscriptions cancel 11 and 15 right and just as a general tip it's always good to ask Grothbot or AI to give you its response in a number list like this to make it super easy for you to just tell it to do things by just referring to the number in the list instead of have to type everything over again. I use this pattern all the time. All right, so now Crockbot is actually taking action, right? This is where the magic happens. You can see here is already unsubscribed to a bunch of senders. It's trashed three Google Drive files that we asked it to and now it's cancelling Lovable and Equipped Foods, which is a protein company. Now to cancel lovable I first have to sign to the cloud computer with my lovable credentials which I did manually and we found out that actually lovable is already scheduled to be cancelled. So lovable is done. Then it asked me to sign to equip foods and I did that and then it cancelled uh the protein subscription for me. By the way, Equip Foods is a great protein company. I'm only canceling because I have too many protein powders at home already. Uh so it basically did all this work, right? trashed a bunch of stuff. It's unsubscribed to a bunch of emails and it's canceled a bunch of subscriptions to save me money. And you can see that it did all this in around five minutes when it would have taken me probably 30 minutes to an hour to do all this manually. Marie Condo is very very useful. Of course, and there's something missing with this bot. I think we should ask it to can you talk like Marie Condo from now on? Give me an example because right now it sounds too much like a robot and not so much like Marie Condo and let's see what it comes up with. All right. So now uh Marie Condo is actually going to talk like Marie Condo. You can see Hermis and the singing have completed their work. We thank them and place them in the trash where they may rest. Equip foods no longer sparks joy and release prime protein subscription with gratitude. Yeah. So now we can set up Marie Condo to maybe talk to us every week or every month to clean up our digital files and spark joy, right? So this is definitely a a bot that I recommend you setting up. Just remember to ask it to give it output in a number list instead of just doing the cleanup for you so that you can review it first, right? You don't want it to accidentally delete some important file. Now let's cover the personal concurge bot. This is a bot that I want to use for all my vacation and travel plans. It has access to my vacation document where I've listed my December trip to Japan. Here's a quick preview of the document. It has the full iterity for Japan that I created with AI as well. Let's go back to Grockbot. And what I want Grockbot to do is I haven't quite booked my flights to Japan yet. So, I wanted to monitor for price changes and alert me on what routes are the best deal. Here's a prompt that I give it. Read my vacation document and monitor the exact flight legs for my family trip. Get the dates, the best options for each flight leg. Check regularly and let me know when the price improves. You see here that I found my flight legs and is using Google flights to check the prices. Now, you may be wondering what's the advantage of using Grockbot for this instead of just setting up Google flight price alerts. And the value here is that Grockbot can understand my whole trip based on my document and decide what's a better option for my family. If you scroll down here, the big finding is that a Tokyo round trip is about $2,700 cheaper than the open jaw flights that my dog prefers. Right? My dog prefers it to fly from SFO to Tokyo and then from Tokyo to Fukoka, which we're going to, and then from Fukuoka back to SFO. But actually, Grockbot found a better itinerary. It's about $2,700 cheaper to just fly round trip to Tokyo instead of doing this itinerary that I laid out, right? A simple Google price alert would not have found this. And now I ask it to check every morning at 9:00 a.m. to see if the price improves. And you can see here that the price is still around the same. The Tokyo round trip is still much cheaper. Eventually, I can ask Rockbot to also just go ahead and book the flight for me or check into the flight when the time comes. And generally speaking, I think it's always a good idea to have a travel thread or travel bot to both help you plan travel ahead of time and also when you're at a location to help you book amusement parks, to help you figure out what to do every single day. So, I imagine I'm going to be using this personal travel concurge a lot. All right, let's test one more use case with Grockbot. Because Grockbot gives me a dedicated cloud computer, I thought it would be fun to ask it to install and let me play some retro games. I asked it to install Red Alert, Doom, and Commander King. And you can see here that it found the files and installed it. So, why don't we just ask it now? Let's say open Doom for us to play. And let's see how things work out. All right, looks like Doom is up. Let's open it in our virtual cloud computer. And here it is. And here we can start a new game. Let's pick this episode. And yeah, let's say Hurt Me Plant Penty. Here's Doom. And here's kind of where Grockbot falls apart a little bit. Unfortunately, because it's on a virtual cloud computer, the mouse isn't quite configured right to actually play Doom. For some reason, it's looking at the floor all the time, and I can't seem to adjust the mouse to actually look up. All right. So, Doom doesn't quite work here right now. Now, let's actually try playing some other game. Let's try asking to play Commander King. I'm not sure if you guys know this, but Commander King is an awesome platform game that I played in my youth. And now it's loading Commander King. So, let's see what it comes up with. Awesome. This is Commander King. Let's see if it plays well or not. Let's start a new game. One player normal difficulty. And here we go. Here we go. It's a very basic platformer, but I remember really enjoy it in my youth. How do I jump? I forgot how to jump. Oh, so control is jump. And yeah, it plays better than Doom for sure, but there is some lag in the keyboard and mouse that makes it difficult to actually control the character. Okay, so um yeah, that's just for fun. But basically, Grockbot is not replacing your gaming PC or GeForce now yet. But the fact that the agent can install and launch these games on its own computer gives you a sense of how open-ended this could become and how much potential there is here. Right? So maybe Space X AI can use all the data centers and GPUs in space to actually deliver AAA games through this virtual cloud computer. That would be a dream, right? And while we're at it, I open this file manager here. And here's all the stuff that we installed into our virtual cloud computer. It kind of looks like Windows 3.1 a little bit. I'm not sure what kind of thing it is. There's Japan flights. There's other stuff here, right? And then there's games that we've installed. And also we have Chrome and a terminal. So that's kind of our virtual cloud computer. All right. Now, All right. Now before we wrap, I want to talk about probably the biggest hurdle for Grobbox adoption, which is trust. When I see a Google sign screen like this on my laptop, I don't really think twice before signing in. But because this appeared on the virtual cloud computer, I hesitated a bit because how do I know that nobody else is seeing this screen on the virtual cloud computer? Now, if you go to the Grogbot website, if you scroll all the way down here, there is a note about privacy here, which is how does Grockbot handle my privacy? Grabbot uses the same cursor SSO off and privacy mode you already trust. Your cloud computers encrypted in transit and at rest and there's no AI training on top of it. Right? So, you know, I'm willing to give Grockbot and the virtual cloud computer access to all this stuff because I'm an early AI adopter, but I can see normal people struggling to understand what this cloud computer thing even is and kind of hesitate to sign into their favorite apps on this device. So, I think the AI Asian platform that figures out trust will be the first to get mass adoption. But overall, I think Grockbot is a clear sign of the future. We're moving away from manually using our keyboard and mouse to do work on our laptops to using our voice to orchestrate a bunch of agents that live in a dedicated cloud computer. And Grockbot is the first product to actually enable this. Now, it's not quite my daily driver yet because I think Chat GPT still offers more for $20 a month while Grockbot requires paying $200 a month to use on a regular basis. But I think Grockbot has much cleaner UI than chat right now and is also very very capable. And overall, it's just great to be in a world where cursor and SpaceX AI are just as viable a competitor as OpenAI and Anthropic. I think cursor may even have the edge if it can continue to support multiple models from all providers. So, Grockbot is available for free and I definitely recommend downloading and trying it to see a glimpse of the future. I'll include some of the prompts from this video in the pin comment below. And I also have an exclusive interview with the Cursor team on how they built Grockbot coming up in the next few weeks. Overall, I'm really impressed by Grockbot. I think the team really cooked here and I can't wait to hear the story behind how they built this. So, please like and subscribe if you enjoy this video and I'll see you next time.