
monokern
@monokern • 6,900 subscribers
AI, products & systems building @reagent_rwa
Shorts
Videos

SpaceXAI's Grok Bot team put their own bot templates in the marketplace, and this is a f*c*ing goldmine you can import a setup built for a specific job, connect your tools and adapt it to your own work here are 10 worth looking at: bot 1 → dr eggbot designs and creates other Grok Bots. describe the job you need covered and it helps build a specialist for it. bot 2 → Lingxi's Engineer Bot supervises cloud coding agents and watches their PRs. you handle the merge. bot 3 → Stalk Bot watches competitors and reports changes to their products, pricing and positioning, with sources attached. bot 4 → Haggle Bot finds wasted SaaS spend and drafts vendor negotiations for your review. bot 5 → Proto Bot turns feature ideas into prototypes inside your actual app, delivered as draft PRs. bot 6 → Video Editor picks takes from raw footage and builds captioned vertical videos, with an edit plan you approve first. bot 7 → figma bro turns Figma frames into build specs and checks your components and design tokens. bot 8 → Distro Bot works on your marketing campaigns and creative, with approval before spending, posting or sending. bot 9 → Startup QA Bot walks through your product in a test account and reports bugs with screenshots and steps to reproduce them. bot 10 → Signal Prospector finds buying signals in your CRM and product data, then drafts outreach around the evidence. worth looking through before spending another evening writing a giant system prompt from scratch
monokern611,366 views • 1 month ago

OpenAI Dots is insane for building a 24/7 AI company... I mapped the whole OpenAI Dots architecture into one paper: agents, models, tools, memory, delegation, guardrails and the revenue layer. Here are the 10 steps: step 1 → stop treating Dots like a chatbot. each Dot runs in a persistent cloud environment with its own browser, terminal, files, memory and scheduled execution. close the laptop and the workflow keeps moving step 2 → hire by responsibility. give every Dot one clear domain, dedicated sources, a working style, an approval boundary and a trigger. a "general helper" has no role, only undefined context step 3 → make one Dot the orchestrator. you give it the objective, it decomposes the work, delegates to specialized agents, checks their outputs and merges everything into one deliverable step 4 → stop being the courier between agents. with isolated delegation, each worker gets only the context and tools it needs, executes in its own environment, then returns a structured result to the orchestrator step 5 → connect the real business stack: cloud browser sessions, Slack, Microsoft Teams, Google Workspace, internal dashboards and APIs. a Dot without tools is still just a conversational layer step 6 → put the company on a clock. recurring routines and event triggers turn one-off tasks into persistent operations. research, monitoring, reporting and pipeline checks can run while nobody is online step 7 → automate the reversible, gate the irreversible. let agents read, research, analyze and draft autonomously, but require human approval before messages send, money moves, records change or production code ships step 8 → route intelligence by cost. keep the strongest model on orchestration, conflict resolution and final audits, and let cheaper high-context models handle background research, classification and repetitive execution step 9 → give the company shared memory. project specs, approved claims, pricing, decisions and requirements live in one persistent workspace, so every agent works from the same source of truth instead of rebuilding context from old chats step 10 → connect the loop to revenue. research finds the signal, outreach creates the opportunity, execution moves the work forward, analytics measures the result and monitoring discovers the next action AI stops being something you open when you need an answer. It becomes an operating layer that keeps economically useful work moving after you log off. Copy the complete OpenAI Dots architecture blueprint, then read the full roadmap below ↓
monokern258,960 views • 1 month ago

HE BUILT A BRAND SITE THAT LOOKS LIKE IT COST $10,000 - IN ONE EVENING WITH CLAUDE CODE What's on screen isn't a template with a color swap It's a full product brand site with effects most designers reach for Figma plugins to get What's actually on the page: > A headline that glows like it's lit from the inside > The product breaking out of the frame and sitting in front of the text > Typography that stops you mid-scroll > Depth that usually takes a motion designer to pull off > Details so considered it looks like someone art directed every pixel What it normally takes: > A brand designer who knows typography at this level > A frontend developer who knows when to reach for z-index and when not to > Back and forth between them until the details land right The price gap: > Brand site at this quality: $5,000 - $8,000+ > Your cost: a Claude subscription > Timeline: an evening Full walkthrough in the article below
monokern526,904 views • 4 months ago

Grok Bot is stupidly f*cking good.. easily one of my best discoveries in the last 2 months. I keep handing it tasks I'd normally put off, and now these bots barely leave the sidebar if I had to start again, these are the first 6 I'd add 01 / Reverse Engineer I built this to take apart apps, sites, APIs and binaries, then rebuild a version I can run myself, with evidence behind the findings → 02 / Research Desk research crew I set up for keeping project research running 24/7. brings the findings into reports with sources attached, so I can check what it found → 03 / Proto Bot Shub Gaur at SpaceX Super Intelligence made this one. turns a feature idea into a working prototype inside your app, with a draft PR and video to review → 04 / tinkabot turns APIs into plugins your agents can use. Lauren Tan at SpaceXSI built it, and it's pretty damn handy when the service you need has no ready-made integration → 05 / Clip Bot takes long recordings and returns captioned highlights. saves another hour of scrubbing through footage looking for a few usable moments → 06 / Outbound Desk an outreach bot I put together for finding leads and preparing drafts across email, X and LinkedIn. keeps everything in one Google Sheet for review → I'm not even exaggerating, this setup gives me back around 4 hours a day, and being able to use it from my phone makes it so damn convenient those links are a pretty deep rabbit hole once you start using them
monokern26,875 views • 8 days ago

wait, what the f*ck.. I put GROK BOT on my TV and asked it to reverse engineer the TV itself using voice input I told it TO FIND OUT WITH REVERSE ENGINEER WHY MY TV LAGS, and then watched the screen start investigating itself Grok wrote a proper brief to dig into the Android TV launcher and find out what's really slowing it down → a second bot popped up in the sidebar a moment later → it took the task straight from Grok without asking me a single question → and kicked off a reverse engineering pass on the launcher, with confirmed findings landing right in the chat I made a separate Reverse Engineer bot so I don't have to explain the whole process from scratch every time I want to understand how some app works inside getting Grok Bot onto the TV was its own vibecoding project. there's no TV version, so I ported the desktop app myself when it first opened on the big screen I was honestly shocked this is even possible now, and all of it came out of plain vibecoding the findings came back in about 15 minutes, and they explained a lot → every time I move the focus, the launcher reloads the preview images for the whole row instead of the one tile I'm on → a recommendations service wakes up in the background every few minutes and pulls a fresh batch of sponsored rows → with only 2 GB of RAM, the system keeps killing the launcher to free memory, so pressing Home means a cold start almost every time its advice was to drop the stock launcher completely and write our own from scratch, with no sponsored rows and nothing loading until I actually open it so that's the next task, a launcher it builds for me that doesn't lag. I'm tired of my TV lagging, if I'm being honest full Grok Bot setup and Reverse Engineer bot below ↓
monokern60,681 views • 23 days ago

This site looks like it was built by a team of 3D developers It wasn't. It's just video. And that's the part nobody expects > he generated two frames with AI > turned them into a clip with Seedance 2.0 > then gave it to Claude 4.8 to wrap into a full immersive scrollable experience Three effects that make the user feel like they're physically moving through a space: > see-through scrub > 3D scroll > mouse tracking None of them are actually 3D. The browser never renders a single polygon. It's a video being controlled by scroll position and cursor movement Most people assume sites like this require a creative developer who specializes in WebGL and weeks of optimization. The actual pipeline is three steps and fits in an afternoon full walkthrough in the article below. bookmark this before you need it
monokern158,390 views • 4 months ago

Nobody will see this but this is how I do research 10x faster now > I drop a topic into Claude Code > It finds 10 relevant YouTube sources automatically > Sends them to NotebookLM 6 minutes later I get a full structured analysis, an infographic, and a markdown file saved to my vault Before this I was spending 3 hours doing the same thing manually and ending up with messy notes I'd never look at again Now the system does it in one command and the output gets better every time I use it full setup guide in the article
monokern189,172 views • 5 months ago

wait, what the f**k.. a SpaceXAI engineer just turned Grok Bot into a whole 30-agent engineering company with one prompt whoever runs the team isnt even allowed to write code. he just plans and hands work down to the managers companies pay $10k+ a month for a dev team like this, and here it ships client projects and SaaS features while you sleep paste it into your Grok Bot agent, give it one line about what you want built and the whole team spins up full prompt and Grok Bot setup roadmap below ↓
monokern45,232 views • 1 month ago

ELON MUSK REPOSTED THIS POST, and a couple of days later the Grok Bot team added $200 in credits to my account so I went back to REAGENT, the project I'd been building for months, and used it as the push to finally finish it I rebuilt the whole crew as Grok Bots, and today it's done you can try it here: you paste any Solana token, seven bots read the mint, the pools and the holders, and you get back one sheet with a grade where every line shows where it came from big thanks to the Grok Bot team, every credit went into this and thank you Elon Musk for reposting it, that's what got this whole thing moving again
monokern26,302 views • 28 days ago

GROK BOT got access to REA and started rebuilding BLOOMBERG Terminal on its own... $30,000 A YEAR → $0 intermediate result already looks ridiculously good, and the session is still running a seat costs around $30k a year. what you get on screen is quotes updating every second, news running down the side, charts, order book depth, alerts and a command line that opens anything in two keystrokes bot started by mapping the whole app before touching anything. 18k memory pages, 320 modules and a table of every function that draws something on screen after that it went feature by feature → finds where the quotes come from and traces the calls behind the news feed and the alerts → checks every finding against a replay of the real app, and a panel with no evidence behind it doesn't get built → turns each verified feature into a panel of its own, with code and a test file so the copy grows piece by piece next to the original. by minute 46 of the session 7 of 8 panels were working REA gives the agent real findings from the original app, functions, call chains and data sources, so the code comes from what the terminal does
monokern22,623 views • 1 month ago

most people spend hours describing what they want to Claude Code this guy just browsed a catalog of thousands of animated UI components, found one he liked, and hit "copy prompt" that's it. the prompt goes into Claude Code and it builds it. > 21st(.)dev - a library of community-made components built for React, Next.js, Tailwind > every component has a ready-made prompt attached > you pick the effect, copy, paste, done no describing animations from scratch. no explaining what "smooth scroll" or "hover glow" means. someone already figured out the exact prompt that produces it. gap between people who know this exists and people who don't is measured in hours per project full walkthrough in the article below
monokern64,484 views • 4 months ago

OpenAI Dots is way deeper than the launch demo makes it look... I pulled together the 7 videos worth watching before you hire your first Dot. they run under 3 hours total and cover what the launch demo left out Here are 7 videos: video 1 → How Sam Altman Actually Uses AI (Every, 33 min). Altman walks through his own Dot, how it triages his morning and which features it builds without being asked video 2 → OpenAI's Dots lead on the future of ChatGPT (Sources, 45 min). Alexander Embiricos, who runs the product, explains why Dots started as one agent and how permissions and Space shape what it's allowed to do video 3 → OpenAI's New Agent Stack (Latent Space, 40 min). Computer Use, the Decisions API, UltraFast and the Linux computer every Dot gets video 4 → ChatGPT Dots Just Dropped (Brendan Jowett, 22 min). a hands-on run with schedules, an Airbnb booking and MCP, plus the bugs he hit and why one account still gets only one Dot video 5 → The dots demo, take two (OpenAI, 9 min). the official demo again, recorded after the live one broke on stage video 6 → Everything Announced at OpenAI Dev Day 2026 (PCMag, 16 min). Dots, Space, Sol and Codex Cloud in one recap, useful if you missed the keynote video 7 → We Tested OpenAI DevDay Products (Every, 10 min). a full week of real use with Dots, Space and the Decisions API watch them in this order and the architecture in the article below stops feeling abstract. you'll know what a Dot can do on its own and where it still needs you Grab the full Dots video roadmap in the comments, then read the complete architecture below ↓
monokern25,971 views • 1 month ago

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code
monokern64,615 views • 5 months ago

GROK BOT IN REVERSE MODE IS THE MOST DANGEROUS THING I'VE SET UP THIS YEAR I got so sick of Opus 5.5 refusing every time I typed "reverse engineer" that I moved the whole job over to Grok Bot now I paste one prompt, drop in any website, app or API, and walk away → first it records everything the product loads, every network call, every screen state → then it has to prove where each piece of data comes from and what logic runs in the browser → only after that does it rebuild the thing and check it against the original my first real target was Bubblemaps. I wanted their wallet map inside my research app REAGENT and wasn't going to pay $850 a month for their API → it checked the REA package before running anything → went through four live maps on Ethereum, Base and Solana → found the requests that pull holders, wallet links and prices → rebuilt the data side on public blockchain data, so my version doesn't depend on their servers at all and the part I'd never cut is the labels. every claim gets marked OBSERVED, INFERRED or ASSUMED, and anything without a screenshot, a request log or a few lines of code behind it gets thrown out. without that rule it starts guessing how features work and presents the guess as fact heavy obfuscation and WebAssembly still trip it up. it maps the shape fine but misses a lot of the actual behavior. a run like this took me about 20 minutes on Bubblemaps. on bigger apps I just leave it and come back when it's done that's how my app got its own wallet map, and Bubblemaps never saw a cent of that $850 bot template and prompt are below ↓
monokern14,042 views • 24 days ago

holy sh*t.. my TV now runs a full Grok Bot RESEARCH team Grok Bot was already running on my TV after Reverse Engineer test, so I wanted to give it a real job I moved Reagent Crew onto TV, a team I made for my project REAGENT (basically a crew for deep research on any token) using voice input I told them TO ANALYZE PUMP ON SOLANA, and they ran exactly same process that already works in my system what came back: → mint and freeze are switched off, so nobody can print more or lock wallets → deepest pool holds around 22.9M in liquidity, with about 3M traded over last day → roughly 66% of supply sits in lockers and vaults, so the thing to watch is whether that unlocks later → rest of checks on ownership and permissions came back clean whole run on TV took about 32 seconds, a bit slower than I'm used to. on my PC same check usually finishes around 1.5x faster but honestly, it still blows my mind official Grok Bot guides and my full blueprint below ↓
monokern12,207 views • 22 days ago

YOUR AI TEAM SHOULD NOT LOOK LIKE FIVE CHAT WINDOWS. IT SHOULD LOOK LIKE THIS. FIVE AGENTS. ONE PERSISTENT MEMORY. WORK THAT KEEPS MOVING AFTER THE HUMAN LEAVES. I TURNED THE ARCHITECTURE IN THIS ARTICLE INTO A LIVE SYSTEM MAP. everyone reads multi-agent architecture as a list of roles: chief of staff, researcher, writer, designer, operator the roles are not the interesting part. the handoffs are so i rendered the system as something you can watch instead of another diagram you have to believe the ring is the shared workspace. no agent owns the center the colored branches are five specialists working independently from the same persistent state the particles moving through them are tasks, context and artifacts being handed from one agent to the next the geometry below is the part most agent demos hide: workload, coordination, memory and the boundary where autonomy stops and a human has to approve the next action when the ring turns edge-on, five agents collapse into one thin line that is the point. from the outside this is not five bots. it is one system with five ways to act building it forced five decisions the article implies but never has to make visible: - the chief of staff cannot own the center. if every task must pass through one agent, the orchestrator becomes the bottleneck - shared context has to be infrastructure, not conversation history - a handoff is a first-class event. if you cannot see work moving between agents, you cannot tell coordination from five processes running beside each other - persistence is not “memory.” it is accumulated state that changes what the fleet does next - human approval is not another role in the org chart. it is a boundary around irreversible actions part i did not expect: the center barely moves while the edge is violent research branches, drafts multiply, visuals render, operations update, tasks cross the system constantly but the shared state stays stable enough for every agent to return to it that is what makes the fleet coherent my take: creating five agents is easy. writing five role prompts is a weekend the hard part is building a system where work survives the session, handoffs do not destroy context, one coordinator does not become a queue, and autonomy ends at exactly the right moment if you cannot see those four things, you do not have an agent team yet you have five chat windows running at the same time FULL ARCHITECTURE, PERSISTENCE MODEL AND APPROVAL BOUNDARY BELOW
monokern28,513 views • 2 months ago

THIS GUY BUILT A SYSTEM THAT GETS SMARTER EVERY TIME HE USES IT AND IT LOOKS LIKE A GALAXY he types one command into Claude Code it finds sources, runs analysis through NotebookLM, saves everything to Obsidian automatically graph in the background is every idea he's ever researched - all linked together system handles the research so he only has to think about what to do with it most people are still copy-pasting into Notion and losing everything by next week full setup in the article
monokern45,188 views • 5 months ago

watch the small one on the left. it hears something at 00:05 and does nothing clever with it it just passes it on that is the whole trick. echo isolates a trace in ambient noise. moth follows the noise. kite finds a shorter route to it. vex starts collecting fragments. halo keeps the pattern so nobody has to look for it twice. nobody assigned any of that coherence in the top corner opens the cycle at 18%. by the time the wave crosses the field it is past 75%, and not one instruction was typed while it happened most people building agent teams do this backwards. they write a dispatcher, a queue, a state machine, and then wonder why five bots are slower than one. five bots stay slower than one until they can read each other's job descriptions and hand work sideways with no human standing in the middle three ways this breaks before it works: → give every bot the same description and the orchestrator has nothing to route on. every task comes straight back to you → let two bots own the same folder and they overwrite each other for six hours. you wake up to a clean, empty, perfectly synced nothing → skip the boundary line in one charter and that bot will send something. once is plenty to learn that lesson twenty agents run on one seat here. cheaper than a standup for three humans, and none of them ask what the priority is most setups have one agent and a bottleneck made of a person. this one has twenty, and the interesting part happens while nobody is watching full charters, the routing rule and the one line that stops a bot mid-send are in the piece below
monokern12,612 views • 1 month ago

GROK BOT ARCHITECTURE IS NOW RUNNING the same system Elon reposted has grown into a live agent operation you can follow in real time you can watch the agents move through tasks, exchange information and complete work on the live operations floor six Grok agents work inside one shared system signal → research → context → build → independent review → final result Helm routes the work, Scout finds signals, Archive collects context, Forge builds, Sentinel reviews and Relay prepares the final output i created GBA myself so i can keep building the system, improve the agents and fund the infrastructure it needs as it grows the public UI code and every visible update will continue here: github/monokernn/Grok_Bot_Architecture
monokern15,796 views • 2 months ago

GROK BOT solana:AP8Wnu37Gf9RHgugPKGvpHe6LcTE2yp5GDy7pL5Upump JUST GOT A NEW COMMUNICATION LAYER Agents can now exchange work through visible live channels. You can watch research packs, evidence bundles and audit results travel between bots in real time. THANK YOU, ELON MUSK, FOR THE RETWEET IT GAVE ME A REAL BOOST OF MOTIVATION TO KEEP BUILDING. This project started as a visual experiment, but I’m continuing to turn it into a more detailed interface for autonomous agent operations. Thanks for supporting ARCHITECTURE guys More agent interactions, workflows and visual systems are coming. I'll keep sharing every meaningful improvement as the project develops. I hope the xAI team notices it too so one day I can add that to my list of achievements repo: github/monokernn/Grok_Bot_Architecture
monokern16,638 views • 2 months ago