so obsessed with @bot had to do a deep dive on this weeks episode of "How I AI" covering my 7 favorite bots + how to set them up 00:00 why i migrated from openclaw to grok bot 07:41 Chief: my chief-of-staff bot 12:41 TradBot: my family agent 19:51 LGTM the PR Closer 22:03 Lockdown: SOC 2 control monitoring bot 24:00 Holly Helpdesk: customer support 26:58 Penny Pincher: money saving bot 29:37 ShopZilla and Sylvie Style: personal shopping 32:54 How to migrate your OpenClaws 📹 full ep on yt:

After less than 24 hours of finally using Grok Bot, here are some of my thoughts: - The UX is incredible! So simple at face value, but so much underneath the hood & pretty much every integration you could ever want - even superhuman email MCP for premium SH subs, which was my #1# need going into it. Everything about this product was designed with care, and I think it's a blast to use. I've yet to set up every integration I need, but it seems to be this is just as capable as every other coding or work agent right now - it's also nice to have a product that's so easily compatible with Cursor, but for more info on this I recommend other posts, I'm not prompting agents to write code *every* day. - There are 100+ (or more?) startups offering agents for consumer use cases, enterprise, in-between, teams of agents, etc etc etc, but none of these can beat the ease of use that comes from Grok Bot. I really like the style of subagent icons and the ability to name them, give them a description, and have a leader agent assign instructions for them - it makes it feel like managing an actual team or talking to coworkers on Signal, not some over engineered or over stylized UI designed for software developers. - Model doesn't matter, which was a big shock for me. Before this I was using GPT 5.6-sol everyday, and was worried that I might not like Grok or Cursor-Grok running my tasks for me, but I have not noticed really a single difference in quality of output. They could be running a no-name model under the hood that no one has heard of, and it doesn't matter, people just want their tasks done correctly and efficiently! - I've seen numerous examples of people autonomously running "money maker" machines, whether it's prediction market arbitrage, perpetual future pair trades, or ecommerce schemes with their teams of Grok Bot agents. I have no opinion on whether these are real or consistently work for people, but based on my brief experience using Grok Bot, all of this seems possible. - The app & site have some cool features, like recording a task/routine and "teaching" the model yourself for later repeated completion without instruction needed. I haven't tried this yet, but will soon attempt it and see how it works. I'm sure this is possible via submitting a screen recording to other coding/work agents, but this just feels so much more personal, and arguably the most killer usecase or feature of Grok Bot. - Overall 10/10 and highly recommend it for people juggling hundreds of emails, DMs, and conversations each day. Just having some type of virtual assistant that can easily pick up on your routine in a simple UX is incredibly welcome.

We're making Grok Bot more widely available. All SuperGrok Plus, Cursor Pro+, and Cursor Teams subscribers now have access. We're also offering a free trial with limited usage for all other users.

So I’ve been using grok @bot for a few days. It’s starting to click Bro they leapfrogged codex app and Claude code entirely. Super app 2.0 Grok bot’s marketing is completely wrong and misleading. It’s not an easy normie friendly chat. Don’t pay attention to the bot or chat UX, that’s not the point. Total distraction. Logo is flat out wrong. They legit did the Shoggoth meme with a smiley face mask in front of an AI demon. Grok bots is actually the highest difficulty, most powerful, and highest skillcap agent harness by far. Super rough around the edges. Dev tool, power user quality, nowhere remotely close to consumer level of approachability. Which is fine, they chose a lane, VSCode dev heavy design sensibilities bleed through, and to be fair it’s in beta. But importantly they nailed a new agent stepping stone: Persistent agent driven cloud computers Progression: - Chat - Chat + Tools, Calculate & Code Interpreter, MCPs - Claude Code & Coding Agent Harnesses: Chat + Tools + Read/Write local Files + Local CLI - Codex/Conductor Super App: Agent Harness + vertical tabs + embedded browser + computer use - Grok Bots: Agent Harness + Computer use + Browser Use + Entire cloud computer with all your files and apps, saved Grok bots absolutely mogs ChatGPT work, and the codex super app + ChatGPT remote. UX of having the cloud computer instance be persistent and not ephemeral per thread is 10000x better. Also you can actually open the computer from your phone and click and type and look at things. It’s not some black box only the agent sees. These were the 2 missing pieces This pattern is about to get copied and adopted by everyone.