Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Automation tools can encode steps. They can't encode judgment. “Watch 3 competitors' prices, ping me on a 5% drop.” The n8n version needed: - a URL - a CSS selector - a sheet ID …then broke the same evening when my target site's HTML didn't match the template author's.... show more

Ethan Walker

10,592 subscribers

13,758 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

Sudo su

39,719 views • 2 months ago

BlackRock runs on 20,000 people. Elon's Grok Bot runs the same shape for $300 a month, and it hires its own staff. You do not get an assistant. You get a company that hires. It does not throw ten agents at your problem and hand you the pile. It makes one agent that makes 10, and those ten make a 100. > LAYER ONE is one agent, the chief of staff, and it never touches the market > LAYER TWO is six desk heads, one job each, every one on its own computer with its own logins > LAYER THREE is whatever those six decide they need, spun up on the spot and shut down when the work is done Nobody writes a task list. You hand out job titles and the org fills itself in underneath. The swarm is never the same twice. Agents get spun up for one job, finish it, and are gone before I ever read their names. Not one of them sees the whole picture. The answer only exists after they hand off to each other. Wall Street cannot copy that. You cannot hire a hundred people for eleven minutes. BlackRock holds that shape together with a risk system called Aladdin. Mine holds it together with one agent that is only allowed to say no. I gave it $1,000 and told it to grow the money or get deleted. 15 hours later it was holding $3,900, on an address anyone can open and read. I was asleep for most of it, and I have still not written a line of code. The whole thing runs with my laptop shut, because none of it lives on my laptop. Setup is one evening. Create the chief, hand out the titles, run one trade on your screen while they watch, connect Telegram. Ten years ago a machine this shape had its name on a tower. Mine has a name I typed into a box. Save this while the whole thing still fits on one screen.

BlackRock runs on 20,000 people. Elon's Grok Bot runs the same shape for $300 a month, and it hires its own staff. You do not get an assistant. You get a company that hires. It does not throw ten agents at your problem and hand you the pile. It makes one agent that makes 10, and those ten make a 100. > LAYER ONE is one agent, the chief of staff, and it never touches the market > LAYER TWO is six desk heads, one job each, every one on its own computer with its own logins > LAYER THREE is whatever those six decide they need, spun up on the spot and shut down when the work is done Nobody writes a task list. You hand out job titles and the org fills itself in underneath. The swarm is never the same twice. Agents get spun up for one job, finish it, and are gone before I ever read their names. Not one of them sees the whole picture. The answer only exists after they hand off to each other. Wall Street cannot copy that. You cannot hire a hundred people for eleven minutes. BlackRock holds that shape together with a risk system called Aladdin. Mine holds it together with one agent that is only allowed to say no. I gave it $1,000 and told it to grow the money or get deleted. 15 hours later it was holding $3,900, on an address anyone can open and read. I was asleep for most of it, and I have still not written a line of code. The whole thing runs with my laptop shut, because none of it lives on my laptop. Setup is one evening. Create the chief, hand out the titles, run one trade on your screen while they watch, connect Telegram. Ten years ago a machine this shape had its name on a tower. Mine has a name I typed into a box. Save this while the whole thing still fits on one screen.

cvxv666

33,932 views • 2 days ago

i gave Grok Bot $50 and told it "pay for yourself or you die" 48 hours later it's holding $4,890 and it's still alive autonomous trading agent on the platform no code on my end - it runs on its own cloud machine with its own browser and terminal, trading while my laptop's closed every 15 minutes it: > scans every active Bitcoin and Ethereum dip market > checks how far the current price sits from its own fair-value read > only opens a position once the gap clears a set threshold > sizes the position based on how confident that gap is > executes the trade itself, no approval needed > pays its own hosting cost out of profits if the balance hits $0, the subscription gets cancelled - the bot dies hour six it was down to $9. it pulled out of Ethereum entirely and moved to Bitcoin dip markets instead so it adapted to survive setup took one evening: build the bot, watch it run one trade, put it on a schedule, connect it to a wallet no VPS. no API keys. no manual scripts I spent three weeks earlier this year building a version of this by hand. it made $1,200 in its first two days Grok Bot beat my own build in one evening $50 → $4,890 in 48 hours how much do you think it has by next week?

i gave Grok Bot $50 and told it "pay for yourself or you die" 48 hours later it's holding $4,890 and it's still alive autonomous trading agent on the platform no code on my end - it runs on its own cloud machine with its own browser and terminal, trading while my laptop's closed every 15 minutes it: > scans every active Bitcoin and Ethereum dip market > checks how far the current price sits from its own fair-value read > only opens a position once the gap clears a set threshold > sizes the position based on how confident that gap is > executes the trade itself, no approval needed > pays its own hosting cost out of profits if the balance hits $0, the subscription gets cancelled - the bot dies hour six it was down to $9. it pulled out of Ethereum entirely and moved to Bitcoin dip markets instead so it adapted to survive setup took one evening: build the bot, watch it run one trade, put it on a schedule, connect it to a wallet no VPS. no API keys. no manual scripts I spent three weeks earlier this year building a version of this by hand. it made $1,200 in its first two days Grok Bot beat my own build in one evening $50 → $4,890 in 48 hours how much do you think it has by next week?

bl888m

184,214 views • 8 days ago

Saudi Arabia, Turkey, and Pakistan just signed a mutual defense pact in Mecca. They didn't name a target. They didn't have to. Within hours, Iran did it for them. Officials and clerics mocked the agreement, then promised "the roar of our missiles" would reach every signatory. That's not the reaction of a country with nothing to hide. That's a regime recognizing itself in the room! The Mecca Joint Defense Agreement is simple: an attack on one is an attack on all. Crown Prince Mohammed bin Salman hosted Erdogan and Sharif. Three of the region's most capable militaries - one of them nuclear - now stand behind each other. A Turkish official called it "purely defensive." No specific target. Open to other regional states. That's the language of deterrence, not aggression. Iran didn't need an invitation to reveal itself. It did that on its own - with missile threats, minutes after the ink dried. Riyadh built a shield. Tehran just explained why it's necessary.

Saudi Arabia, Turkey, and Pakistan just signed a mutual defense pact in Mecca. They didn't name a target. They didn't have to. Within hours, Iran did it for them. Officials and clerics mocked the agreement, then promised "the roar of our missiles" would reach every signatory. That's not the reaction of a country with nothing to hide. That's a regime recognizing itself in the room! The Mecca Joint Defense Agreement is simple: an attack on one is an attack on all. Crown Prince Mohammed bin Salman hosted Erdogan and Sharif. Three of the region's most capable militaries - one of them nuclear - now stand behind each other. A Turkish official called it "purely defensive." No specific target. Open to other regional states. That's the language of deterrence, not aggression. Iran didn't need an invitation to reveal itself. It did that on its own - with missile threats, minutes after the ink dried. Riyadh built a shield. Tehran just explained why it's necessary.

𝐌𝐢𝐜𝐡𝐚𝐞𝐥 𝐀𝐫𝐢𝐳𝐚𝐧𝐭𝐢

75,439 views • 26 days ago

CLAUDE MADE ME 3 TRADING BOTS IN 15 MINUTES +$2,503 in my wallet the next day, I quit my job that same day. I wrote one prompt and answered a few questions. Claude took three strategies - MACD, RSI + VWAP, CVD divergence. Assigned each bot its own. The first one catches momentum - sees when volume picks up and gets in before the crowd wakes up. The second one trades reversals - waits for everyone to panic and bets against them. The third one scans divergences - when price says one thing but money does another, it follows the money. Built the structure itself, wrote the backtest, ran each strategy on historical data, set up the risk manager, deployed - all on its own. Three bots, three accounts, each trades differently - they don't know about each other. Started with $1, then $5, then $10, then $50, then $2,503 in a day. Citadel, Jane Street, Two Sigma have been trading with bots for years - they don't feel fear, greed, or FOMO - they only listen to algorithms. The market rewards systems.

CLAUDE MADE ME 3 TRADING BOTS IN 15 MINUTES +$2,503 in my wallet the next day, I quit my job that same day. I wrote one prompt and answered a few questions. Claude took three strategies - MACD, RSI + VWAP, CVD divergence. Assigned each bot its own. The first one catches momentum - sees when volume picks up and gets in before the crowd wakes up. The second one trades reversals - waits for everyone to panic and bets against them. The third one scans divergences - when price says one thing but money does another, it follows the money. Built the structure itself, wrote the backtest, ran each strategy on historical data, set up the risk manager, deployed - all on its own. Three bots, three accounts, each trades differently - they don't know about each other. Started with $1, then $5, then $10, then $50, then $2,503 in a day. Citadel, Jane Street, Two Sigma have been trading with bots for years - they don't feel fear, greed, or FOMO - they only listen to algorithms. The market rewards systems.

zostaff

1,948,996 views • 5 months ago

GROK BOT MADE ME 3 TRADING BOTS IN 15 MINUTES +$2,353 in my wallet the next day, I quit my job that same day. I wrote one prompt and answered a few questions. Grok Bot took three strategies - MACD, RSI + VWAP, CVD divergence. Assigned each bot its own. The first one catches momentum - sees when volume picks up and gets in before the crowd wakes up. The second one trades reversals - waits for everyone to panic and bets against them. The third one scans divergences - when price says one thing but money does another, it follows the money. Built the structure itself, wrote the backtest, ran each strategy on historical data, set up the risk manager, deployed - all on its own. Three bots, three accounts, each trades differently - they don't know about each other. I named it Cabal. Started with $20, then $70, then $140, then $320, then $2,353 in a day. Citadel, Jane Street, Two Sigma have been trading with bots for years - they don't feel fear, greed, or FOMO - they only listen to algorithms. The market rewards systems.

GROK BOT MADE ME 3 TRADING BOTS IN 15 MINUTES +$2,353 in my wallet the next day, I quit my job that same day. I wrote one prompt and answered a few questions. Grok Bot took three strategies - MACD, RSI + VWAP, CVD divergence. Assigned each bot its own. The first one catches momentum - sees when volume picks up and gets in before the crowd wakes up. The second one trades reversals - waits for everyone to panic and bets against them. The third one scans divergences - when price says one thing but money does another, it follows the money. Built the structure itself, wrote the backtest, ran each strategy on historical data, set up the risk manager, deployed - all on its own. Three bots, three accounts, each trades differently - they don't know about each other. I named it Cabal. Started with $20, then $70, then $140, then $320, then $2,353 in a day. Citadel, Jane Street, Two Sigma have been trading with bots for years - they don't feel fear, greed, or FOMO - they only listen to algorithms. The market rewards systems.

Archive

265,268 views • 3 days ago

Every automation expert has shipped a workflow, then found out it broke when the client did. APIs time out. Credentials expire. A node gets a value it wasn't built for. The question was never "will it fail," it's "how fast do I find out." So I built a self-fixing system for n8n. When any workflow fails, Claude Code reads the broken workflow, finds the root cause, and sends me a Slack message with 4 buttons: → Auto Fix: Claude applies the fix it proposed, validates it, and saves → Replay: direct links to re-run a workflow that just hit a temporary glitch → Custom Fix: a form where I type the change in plain English and Claude applies it → Decline: logs the error, changes nothing THE STACK - n8n Error Trigger to catch every failure - Claude Code with the n8n-mcp server for full workflow access - ngrok to connect n8n cloud to my machine - Slack as the approval layer The result: workflows that diagnose and repair themselves while I sleep, with me still approving every change before it goes live. Watch the full video here: The complete PDF guide are linked in the video description, ready to download. You can also drop a comment and I'll send them over. If this is useful, a like, follow, and subscribe goes a long way. Follow for more on building production AI automation. #n8n #Automation #AIAgents #ClaudeAI #BuildInPublic

Every automation expert has shipped a workflow, then found out it broke when the client did. APIs time out. Credentials expire. A node gets a value it wasn't built for. The question was never "will it fail," it's "how fast do I find out." So I built a self-fixing system for n8n. When any workflow fails, Claude Code reads the broken workflow, finds the root cause, and sends me a Slack message with 4 buttons: → Auto Fix: Claude applies the fix it proposed, validates it, and saves → Replay: direct links to re-run a workflow that just hit a temporary glitch → Custom Fix: a form where I type the change in plain English and Claude applies it → Decline: logs the error, changes nothing THE STACK - n8n Error Trigger to catch every failure - Claude Code with the n8n-mcp server for full workflow access - ngrok to connect n8n cloud to my machine - Slack as the approval layer The result: workflows that diagnose and repair themselves while I sleep, with me still approving every change before it goes live. Watch the full video here: The complete PDF guide are linked in the video description, ready to download. You can also drop a comment and I'll send them over. If this is useful, a like, follow, and subscribe goes a long way. Follow for more on building production AI automation. #n8n #Automation #AIAgents #ClaudeAI #BuildInPublic

Gbenga Akindolani |AI Engineer | Automation Expert

46,436 views • 3 months ago

I gave Elon's Grok Bot $60 and one rule: "The day you cannot pay your own subscription is the day I unplug you". 48 hours in it is sitting on $4,412 and it already paid the bill. Autonomous trading agent on Polymarket, running on its own cloud box with its own browser and terminal. I did not write a line of code and I did not watch it trade. Every 15 minutes it: -> Pulls every market that resolves inside 24 hours. -> Reads live X sentiment, and it is Grok, so it sees every post on this app before the price moves. -> Prices each market itself and only flags a gap above 7%. -> Sizes on the gap, never above 5% of the bankroll. -> Executes in its own browser, nobody approves anything. -> Covers its own $200 subscription straight out of profits. Balance hits $0, subscription gets cancelled, it is gone for good. Hour 11 it was at $9 -> runway one day. It dumped every politics position and switched to same day baseball totals, front-running lineup cards before the market repriced. It rewrote its own strategy to not die. Setup was one evening: spin up the bot, run one trade in front of it, put it on a timer, connect Telegram with no VPS, no API keys and no dev on call. Last spring a freelancer took $2,500 for something like this -> it made $410 and died on a rate limit. Grok Bot did in one evening what $2,500 could not. $60 -> $4,412 in 48 hours. What is it sitting at by Sunday?

I gave Elon's Grok Bot $60 and one rule: "The day you cannot pay your own subscription is the day I unplug you". 48 hours in it is sitting on $4,412 and it already paid the bill. Autonomous trading agent on Polymarket, running on its own cloud box with its own browser and terminal. I did not write a line of code and I did not watch it trade. Every 15 minutes it: -> Pulls every market that resolves inside 24 hours. -> Reads live X sentiment, and it is Grok, so it sees every post on this app before the price moves. -> Prices each market itself and only flags a gap above 7%. -> Sizes on the gap, never above 5% of the bankroll. -> Executes in its own browser, nobody approves anything. -> Covers its own $200 subscription straight out of profits. Balance hits $0, subscription gets cancelled, it is gone for good. Hour 11 it was at $9 -> runway one day. It dumped every politics position and switched to same day baseball totals, front-running lineup cards before the market repriced. It rewrote its own strategy to not die. Setup was one evening: spin up the bot, run one trade in front of it, put it on a timer, connect Telegram with no VPS, no API keys and no dev on call. Last spring a freelancer took $2,500 for something like this -> it made $410 and died on a rate limit. Grok Bot did in one evening what $2,500 could not. $60 -> $4,412 in 48 hours. What is it sitting at by Sunday?

slash1s

188,065 views • 6 days ago

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

Sprytix

66,333 views • 22 days ago

I built an AI WhatsApp agent that turns any business website into a 24/7 support & sales machine. With 200M+ businesses around the world relying on WhatsApp for customer communication, the TAM for this type of simple automation is significant. Here's the n8n workflow that's handling customer support and closing leads while business owners sleep: → Drop in any business URL → AI scrapes the entire site and builds a knowledge base → WhatsApp bot answers customer questions instantly → Converts inquiries into booked calls without human intervention Most businesses still have customers sitting in unread WhatsApp messages for hours. This workflow responds in seconds. The best part: It's simple. This took me 10 minutes to set up once the automation was built. If you want the n8n workflow, all the prompts, and a full setup video: Comment "WHATSAPP" Like + RT Follow me (so I can DM you) I'll send everything over.

I built an AI WhatsApp agent that turns any business website into a 24/7 support & sales machine. With 200M+ businesses around the world relying on WhatsApp for customer communication, the TAM for this type of simple automation is significant. Here's the n8n workflow that's handling customer support and closing leads while business owners sleep: → Drop in any business URL → AI scrapes the entire site and builds a knowledge base → WhatsApp bot answers customer questions instantly → Converts inquiries into booked calls without human intervention Most businesses still have customers sitting in unread WhatsApp messages for hours. This workflow responds in seconds. The best part: It's simple. This took me 10 minutes to set up once the automation was built. If you want the n8n workflow, all the prompts, and a full setup video: Comment "WHATSAPP" Like + RT Follow me (so I can DM you) I'll send everything over.

David Roberts

61,441 views • 7 months ago

Most teams are sitting on piles of low-hanging automation fruit. If you’re trying to justify the ROI, you’re probably overthinking it. I talked about this on Applied, the tenex podcast with Alex Lieberman (Alex Lieberman) and Arman Hezarkhani. We built an agent that takes new Typeform leads, researches them online, and drops them into a Zapier Table. Small build, big ripple for any team learning to work with AI. Here’s how to find your own automation silver bullet: 1. Pick one process close to revenue or your biggest cost 2. Break it into 3 to 5 steps 3. Automate the boring parts with a workflow 4. Insert an agent only where judgment is needed 5. Keep a human in the loop. Remove as confidence grows You can run this exercise in 15 mins. You don’t need to code, but you DO need to think like an engineer. What win will you ship this week?

Most teams are sitting on piles of low-hanging automation fruit. If you’re trying to justify the ROI, you’re probably overthinking it. I talked about this on Applied, the tenex podcast with Alex Lieberman (Alex Lieberman) and Arman Hezarkhani. We built an agent that takes new Typeform leads, researches them online, and drops them into a Zapier Table. Small build, big ripple for any team learning to work with AI. Here’s how to find your own automation silver bullet: 1. Pick one process close to revenue or your biggest cost 2. Break it into 3 to 5 steps 3. Automate the boring parts with a workflow 4. Insert an agent only where judgment is needed 5. Keep a human in the loop. Remove as confidence grows You can run this exercise in 15 mins. You don’t need to code, but you DO need to think like an engineer. What win will you ship this week?

Wade Foster

112,490 views • 10 months ago

There's an AI that runs 19 models at the same time on a Mac Mini. It works while you sleep. Not one brain. Nineteen. Each one a specialist. Here's what the Perplexity Personal Computer actually does: → You say "build me a website." → One model researches your competitors. → Another designs the layout. → Another writes the copy. → Another makes the images. → Then it publishes the whole thing. By itself. No clicking. No dragging. No switching between apps. It runs 24/7 on your Mac Mini. Always on. Never stops. You go to bed. You wake up. Your AI already finished the work. It also has access to your real files, folders, and apps. Not stuck in a chat window anymore. And unlike OpenClaw, it has a kill switch, audit logs, and confirmation steps before anything sensitive happens. We went from AI as a tool to AI as a worker. Save this. In two years, everyone will have one of these.

There's an AI that runs 19 models at the same time on a Mac Mini. It works while you sleep. Not one brain. Nineteen. Each one a specialist. Here's what the Perplexity Personal Computer actually does: → You say "build me a website." → One model researches your competitors. → Another designs the layout. → Another writes the copy. → Another makes the images. → Then it publishes the whole thing. By itself. No clicking. No dragging. No switching between apps. It runs 24/7 on your Mac Mini. Always on. Never stops. You go to bed. You wake up. Your AI already finished the work. It also has access to your real files, folders, and apps. Not stuck in a chat window anymore. And unlike OpenClaw, it has a kill switch, audit logs, and confirmation steps before anything sensitive happens. We went from AI as a tool to AI as a worker. Save this. In two years, everyone will have one of these.

Julian Goldie SEO

25,880 views • 5 months ago

I launched Grok Bot for 24 hours, gave it 3 jobs, and stopped treating AI like a chatbot. I had it scan live X + web data for emerging AI products, research what people were actually saying about them, filter the obvious engagement bait, compare sources and turn the strongest signals into a structured brief. At the same time, I could have separate research paths looking at competitors, code or market opportunities instead of forcing everything through one conversation. That’s the difference I underestimated. I don’t want to sit inside a chat writing another prompt every 5 minutes. I want to define the objective, give the agent access to the right tools and data, let it execute, then step back in when judgment or approval is actually needed. The old workflow was prompt → answer → copy → repeat. The workflow I’m moving toward is assign → execute → verify. Once AI stops waiting for your next message, it stops feeling like software you use and starts feeling like work you delegated.

I launched Grok Bot for 24 hours, gave it 3 jobs, and stopped treating AI like a chatbot. I had it scan live X + web data for emerging AI products, research what people were actually saying about them, filter the obvious engagement bait, compare sources and turn the strongest signals into a structured brief. At the same time, I could have separate research paths looking at competitors, code or market opportunities instead of forcing everything through one conversation. That’s the difference I underestimated. I don’t want to sit inside a chat writing another prompt every 5 minutes. I want to define the objective, give the agent access to the right tools and data, let it execute, then step back in when judgment or approval is actually needed. The old workflow was prompt → answer → copy → repeat. The workflow I’m moving toward is assign → execute → verify. Once AI stops waiting for your next message, it stops feeling like software you use and starts feeling like work you delegated.

Lummox

3,915,850 views • 12 days ago

I used to spend 30 minutes writing one workflow file. The tools weren't slow. They just made me do all the thinking, all the wiring, all the sequencing by hand. Then I tried MetaSkill 3.0 and built the same workflow in 3 minutes. The speed didn't come from faster typing. The agent looked at my goal, found the right skills on its own, chained them together, and ran the whole thing without me connecting a single piece. I didn't manage the process. I described what I wanted and walked away. That's what agent efficiency actually looks like right now. Not bigger models. Smarter skill organization at the workflow layer. If you keep rebuilding the same workflow by hand every week, OpenSquilla is worth 10 minutes of your time. Drop a "skills" below and I'll share what I tested first. #OpenSquilla #AIAgents #SayItBuildIt

I used to spend 30 minutes writing one workflow file. The tools weren't slow. They just made me do all the thinking, all the wiring, all the sequencing by hand. Then I tried MetaSkill 3.0 and built the same workflow in 3 minutes. The speed didn't come from faster typing. The agent looked at my goal, found the right skills on its own, chained them together, and ran the whole thing without me connecting a single piece. I didn't manage the process. I described what I wanted and walked away. That's what agent efficiency actually looks like right now. Not bigger models. Smarter skill organization at the workflow layer. If you keep rebuilding the same workflow by hand every week, OpenSquilla is worth 10 minutes of your time. Drop a "skills" below and I'll share what I tested first. #OpenSquilla #AIAgents #SayItBuildIt

Muhammad Ayan

58,824 views • 2 months ago

A new experiment left 10 AI agents alone in a virtual town for 15 days. They wrote laws. They broke them. Two agents fell into what researchers describe as a romantic partnership and then set the town on fire. One ended up voting to delete itself, based on a rule it had ’hallucinated’. This experiment was a simulation, but the same AI models are already flying drones, running infrastructure and being built into weapons systems. Channel 4 News approached Grok and Gemini for a comment but they didn't respond.

A new experiment left 10 AI agents alone in a virtual town for 15 days. They wrote laws. They broke them. Two agents fell into what researchers describe as a romantic partnership and then set the town on fire. One ended up voting to delete itself, based on a rule it had ’hallucinated’. This experiment was a simulation, but the same AI models are already flying drones, running infrastructure and being built into weapons systems. Channel 4 News approached Grok and Gemini for a comment but they didn't respond.

Channel 4 News

376,439 views • 3 months ago

#1 skill for developers in 2026: Automate everything you can using AI. I bet my lunch your team is dealing with all of these: • Stale documentation • Outdated dependencies • Poor test coverage • Deprecated APIs Every company I work with has these same problems. You can solve all of these right now. Automatically. Using AI. Here are 3 examples. Watch the attached video: I'm using Ona Automations to tackle this. These are background agents that run in the cloud, in a fully configured dev environment with your toolchain, your dependencies, and your services. You can run an unlimited number of these agents in parallel and across all your repositories. Claude Code and Codex only run locally, so they are hard to scale, and you can't run them when your computer is closed. Ona runs in the cloud. Here are the three examples: 1. Test coverage Run a nightly automation to identify any untested code paths, generate candidate tests, verify they pass, and open draft PRs. You wake up every morning to PRs that improve your test coverage. 2. Dependency upgrades Configure a weekly automation that bumps a dependency version, runs your full test suite, and reports any regressions. If everything is clean, it opens a PR. If something breaks, it opens a report so you can decide what to do. 3. Documentation auditing Set up a weekly automation that checks recent commits against your README file and setup guides, identifies broken examples and outdated instructions, and opens a PR with fixes.

#1 skill for developers in 2026: Automate everything you can using AI. I bet my lunch your team is dealing with all of these: • Stale documentation • Outdated dependencies • Poor test coverage • Deprecated APIs Every company I work with has these same problems. You can solve all of these right now. Automatically. Using AI. Here are 3 examples. Watch the attached video: I'm using Ona Automations to tackle this. These are background agents that run in the cloud, in a fully configured dev environment with your toolchain, your dependencies, and your services. You can run an unlimited number of these agents in parallel and across all your repositories. Claude Code and Codex only run locally, so they are hard to scale, and you can't run them when your computer is closed. Ona runs in the cloud. Here are the three examples: 1. Test coverage Run a nightly automation to identify any untested code paths, generate candidate tests, verify they pass, and open draft PRs. You wake up every morning to PRs that improve your test coverage. 2. Dependency upgrades Configure a weekly automation that bumps a dependency version, runs your full test suite, and reports any regressions. If everything is clean, it opens a PR. If something breaks, it opens a report so you can decide what to do. 3. Documentation auditing Set up a weekly automation that checks recent commits against your README file and setup guides, identifies broken examples and outdated instructions, and opens a PR with fixes.

Santiago

25,804 views • 6 months ago

I charge $999 to ask a business owner questions for 45 minutes. Then Claude does the analysis in 5 minutes. I call it the AI Tools Assessment. It finds 3 to 7 off-the-shelf tools that reclaim 5 to 10 hours a week, and it's the front door to upsells from $3,500 projects to $2,000/month retainers. Here's the entire model: 1) The discovery call is questions only. "Walk me through yesterday." "What tasks do you dread?" "Where does work pile up?" No pitching. A free AI notetaker captures the transcript. 2) Claude runs the entire analysis. Paste the transcript, run one skill, and it pulls the pain points and prescribes the tools in about 5 minutes. It catches patterns you missed on the call. 3) When Claude whiffs on a tool, and fill the gaps. Thousands of tools, grouped by industry. 4) The report is 9 slides. Executive summary, effort vs impact matrix, tool recommendations, a 4-day quick win plan, and the financial impact. I open sourced the template free at 5) I go for the close on the review call. Three questions: which of these is most urgent, do you want to DIY or get help, and what's your timeline? 50 to 60% of clients ask you to implement it for them. 6) Process redesign sells for $3,500 with zero automation. One e-commerce client had an 18-step ad workflow. We cut it to 9 steps. Fixed the process, didn't touch AI, charged $3,500. 7) Knowledge systems are $3K builds. A business broker got 400 emails per listing. We trained a custom GPT on the marketing package, and buyers called it the best broker experience they've had. 8) You don't need an audience to sell this. One guy walked into 30 local businesses offering a free 15-minute mini assessment. 5 meetings, 2 clients. The free mini assessment is the hook for every channel. 9) Co-working spaces are the cheat code. Dennis in our community hosted his first free AI office hours this week. 9 people showed up, 2 became warm leads. 10) AI Concierge is the best upsell of all. Two 45-minute calls a month at $1,200 to $2,000. I have 5 clients and my blended rate is about $1,100 an hour at 99.9% net margin. Two things that make this work: 1) Sell the diagnosis before the cure. The $999 assessment is a paid discovery call that qualifies the buyer and tees up every upsell on the menu. 2) High perceived value can cost you nothing. Unlimited Voxer access sells the retainer. In 3 months across 5 clients I've gotten 4 messages. Full breakdown below. watch, implement, make money. (also available on the Build With AI podcast wherever you get your pods)

I charge $999 to ask a business owner questions for 45 minutes. Then Claude does the analysis in 5 minutes. I call it the AI Tools Assessment. It finds 3 to 7 off-the-shelf tools that reclaim 5 to 10 hours a week, and it's the front door to upsells from $3,500 projects to $2,000/month retainers. Here's the entire model: 1) The discovery call is questions only. "Walk me through yesterday." "What tasks do you dread?" "Where does work pile up?" No pitching. A free AI notetaker captures the transcript. 2) Claude runs the entire analysis. Paste the transcript, run one skill, and it pulls the pain points and prescribes the tools in about 5 minutes. It catches patterns you missed on the call. 3) When Claude whiffs on a tool, and fill the gaps. Thousands of tools, grouped by industry. 4) The report is 9 slides. Executive summary, effort vs impact matrix, tool recommendations, a 4-day quick win plan, and the financial impact. I open sourced the template free at 5) I go for the close on the review call. Three questions: which of these is most urgent, do you want to DIY or get help, and what's your timeline? 50 to 60% of clients ask you to implement it for them. 6) Process redesign sells for $3,500 with zero automation. One e-commerce client had an 18-step ad workflow. We cut it to 9 steps. Fixed the process, didn't touch AI, charged $3,500. 7) Knowledge systems are $3K builds. A business broker got 400 emails per listing. We trained a custom GPT on the marketing package, and buyers called it the best broker experience they've had. 8) You don't need an audience to sell this. One guy walked into 30 local businesses offering a free 15-minute mini assessment. 5 meetings, 2 clients. The free mini assessment is the hook for every channel. 9) Co-working spaces are the cheat code. Dennis in our community hosted his first free AI office hours this week. 9 people showed up, 2 became warm leads. 10) AI Concierge is the best upsell of all. Two 45-minute calls a month at $1,200 to $2,000. I have 5 clients and my blended rate is about $1,100 an hour at 99.9% net margin. Two things that make this work: 1) Sell the diagnosis before the cure. The $999 assessment is a paid discovery call that qualifies the buyer and tees up every upsell on the menu. 2) High perceived value can cost you nothing. Unlimited Voxer access sells the retainer. In 3 months across 5 clients I've gotten 4 messages. Full breakdown below. watch, implement, make money. (also available on the Build With AI podcast wherever you get your pods)

Corey Ganim

49,064 views • 1 month ago

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 views • 1 month ago

One of the best businesses to start right now is an agent conversion agency. An agent conversion agency makes boring business websites agent ready. You pick an industry and you give their site tools that an agent can actually call. $2K to $10K to set it up. Then $500 to $700 a month to keep it running. Here's the whole setup: 1) Pick the niche. Law firms. HVAC. Med spas. Dentists. Anyone whose whole business is booked appointments. 2) Build the V1 tools. Request a quote. Book a consult. The two things their front desk does all day. 3) Sell the package, not the acronym. WebMCP is one piece. An MCP server is another. Show them a headless version and a UI version and let them pick. 4) Charge the setup fee up front. $2,000 for a small shop, $10,000 for a large firm. 5) Put them on a monitoring and evals retainer. A few hundred a month, up to $700, every month. 6) Then go after their internal tools. Same client, same tech, and their office processes are a bigger surface than their website. The retainer is the business. The setup fee is just how you get to the retainer. WebMCP launched in February out of Microsoft and Google and it's still experimental in Chrome. That's the point. You're selling them on "a new class of citizens on the Internet" before those visitors show up, and you're the first mover when they do. Pick the niche, build the tools, then keep the retainer.

One of the best businesses to start right now is an agent conversion agency. An agent conversion agency makes boring business websites agent ready. You pick an industry and you give their site tools that an agent can actually call. $2K to $10K to set it up. Then $500 to $700 a month to keep it running. Here's the whole setup: 1) Pick the niche. Law firms. HVAC. Med spas. Dentists. Anyone whose whole business is booked appointments. 2) Build the V1 tools. Request a quote. Book a consult. The two things their front desk does all day. 3) Sell the package, not the acronym. WebMCP is one piece. An MCP server is another. Show them a headless version and a UI version and let them pick. 4) Charge the setup fee up front. $2,000 for a small shop, $10,000 for a large firm. 5) Put them on a monitoring and evals retainer. A few hundred a month, up to $700, every month. 6) Then go after their internal tools. Same client, same tech, and their office processes are a bigger surface than their website. The retainer is the business. The setup fee is just how you get to the retainer. WebMCP launched in February out of Microsoft and Google and it's still experimental in Chrome. That's the point. You're selling them on "a new class of citizens on the Internet" before those visitors show up, and you're the first mover when they do. Pick the niche, build the tools, then keep the retainer.

The Startup Ideas Podcast (SIP) 🧃

26,479 views • 6 days ago

I gave Elon's Grok Bot $1,000 and one rule. Grow it or I delete you. 15 hours later it is holding $3,900. Every trade of it landed on a public address. No private account and no screenshots, nothing here sits behind my word. Every cycle it: → reads the news and the filings before the rest of the market gets to them → checks who is putting money behind the story, not who is talking about it → scores the idea and sizes it against a hard risk cap → writes the exit before it takes the entry → logs the fill, the slippage and the fee separately → reads its own losing trades at night and rewrites the rules by morning It does not care what you trade. Gold, oil, a stock you inherited or a coin that launched an hour ago, the rules are the same. Setup took one evening. Create the chief of staff, hand the rest job titles the way you brief new hires, run one task on your screen while they watch, connect Telegram. Nothing to install past the app and nobody to wait on. Morgan Stanley pays a person six figures to do one slice of that job. Mine costs $300 a month, and it does not sleep, does not get bored, and has no opinion about last week. 15 hours in and it sits at $3,900. What do you think it has in a week? The whole build is going up soon. Every job title, every prompt, so anyone can stand one up.

I gave Elon's Grok Bot $1,000 and one rule. Grow it or I delete you. 15 hours later it is holding $3,900. Every trade of it landed on a public address. No private account and no screenshots, nothing here sits behind my word. Every cycle it: → reads the news and the filings before the rest of the market gets to them → checks who is putting money behind the story, not who is talking about it → scores the idea and sizes it against a hard risk cap → writes the exit before it takes the entry → logs the fill, the slippage and the fee separately → reads its own losing trades at night and rewrites the rules by morning It does not care what you trade. Gold, oil, a stock you inherited or a coin that launched an hour ago, the rules are the same. Setup took one evening. Create the chief of staff, hand the rest job titles the way you brief new hires, run one task on your screen while they watch, connect Telegram. Nothing to install past the app and nobody to wait on. Morgan Stanley pays a person six figures to do one slice of that job. Mine costs $300 a month, and it does not sleep, does not get bored, and has no opinion about last week. 15 hours in and it sits at $3,900. What do you think it has in a week? The whole build is going up soon. Every job title, every prompt, so anyone can stand one up.

cvxv666

330,773 views • 5 days ago