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.

Claude Code doesn't replace n8n. Here's one project built with both People think Claude Code replaces n8n. So here's one real project: a returns desk for a small online shop, built with both. Step 1: Claude Code builds the app. The owner says one sentence ("Build me a returns... page"). Claude Code does three things: It reads CLAUDE.md, the shop's handbook of name, colours and rules, which loads every session. It pulls the refund-policy skill. Skills are loaded only when they're needed. It writes the code, hits an error, fixes it, and ships a real returns page. Step 2: n8n wires it into the business. Every return fires a webhook, and the same route runs every time: the label goes out through Gmail a row is added to the spreadsheet a note is posted in Slack the refund goes through Stripe when the parcel is scanned back in Every run is logged, and it runs 24/7. Step 3: a routine does the thinking. Every night at 11, a Claude Code routine runs in Anthropic's cloud with the laptop closed. It reads the day's returns, spots that 6 of 9 mention the same seam, and writes the owner a report. The handoffs: Claude Code wrote the n8n workflow, and n8n calls Claude when a return doesn't fit any route. Claude Code builds and thinks. n8n runs the same routes all day. Together they run the business. #claudecode #aiautomation #aiagent #n8nshow more

Professor Glitch

114,300 subscribers

10,200 views • 1 month ago •via TikTok

Finance Science & Technology #claudecode #aiautomation #aiagent #n8n

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How to build a $25K website with AI, every click from zero (Claude Code + n8n, beginner guide) An agency would charge about twenty-five thousand dollars for this website. Here's how you build it with AI, from zero, every click, and wire it so every good lead gets a real answer in under a minute. You never type code: at every step you say one sentence to Claude, and it does the work. What you need: a paid Claude plan (Pro is enough) and a few free accounts: GitHub, n8n, Resend, Vercel, plus an Anthropic console account with $5 of credit. The Cloudflare tunnel needs no account. The steps, and the exact sentences to say: 1. Download VS Code. Open Extensions, search "Claude Code", click Install, click the spark icon and sign in. Make an empty folder called alder-slate and open it. 2. Say: "Interview me about my business, then write CLAUDE.md." Answer its questions in plain words. CLAUDE.md is the brief Claude reads every time: colors, fonts, services and rules (no stock photos, no purple gradients). 3. Say: "Build the website from CLAUDE.md, with a big serif headline, lots of space, real-looking photos, and a five-step quote form." For a real client, use their real job photos. 4. Say: "Take screenshots of every page on a laptop and a phone, look at them, and fix what's off." 5. The form goes to the website's own server first, which adds a secret password from the .env file (a locked drawer for your keys) before passing the request to n8n. The browser never sees it. 6. Create a free GitHub account. Say: "Put this project on my GitHub." Open the link Claude gives you, type the code, click Continue, then Authorize. 7. Say: "Set up n8n on my computer." Create the owner account, then Settings, n8n API, create an API key and copy it (you only see it once). In the Anthropic console, add $5 of credit and create an API key. 8. Say: "Connect yourself to my n8n, here are the two keys." Claude adds the n8n MCP (a connector that lets Claude work inside n8n). Type /mcp in a new conversation and n8n shows connected. 9. Say: "Add a workflow to CLAUDE.md. When the website sends a new project request, save it to a leads table, check the ZIP code and budget with simple rules, have Claude score it and write a reply, then email Marco and the customer." Then: "Now build that workflow in n8n." 10. Create a free Resend account, API Keys, create, copy. Say: "Use this key to send the emails from n8n." Until you add your own domain, every email comes to you. 11. Say: "Add a daily follow-up, and alert Marco if anything breaks." 12. Say: "Give my n8n webhook a public address with a Cloudflare tunnel, and only let the webhook through." The editor stays closed; the webhook still asks for the password. 13. On Vercel, Continue with GitHub, Add New, Project, Import. Ask Claude: "Which environment variables does Vercel need?" Paste the two (the webhook address and the secret), Deploy. 14. Before real customers: n8n on a real server set to your time zone, your own domain in Vercel and the Pro plan, and verify your domain in Resend. 15. Say: "Install Cloudflare's security audit skill from GitHub." Then: "Security audit this codebase." Then: "Fix what you found." Finally, make fresh keys in every app and swap them in. If you don't even know what I'm talking about and you want to learn all of this from scratch, I break every step down inside my community. If you're interested, the link is in my profile. #claudecode #n8n #aiautomation #vibecoding

Professor Glitch

20,000 views • 28 days ago

n8n is obsolete! Claude Code Builds Faster and 10x easier ##n8n##claude

n8n is obsolete! Claude Code Builds Faster and 10x easier ##n8n##claude

Jonathan Acuña - Doctor AI

10,000 views • 10 months ago

How to put an AI agent to work this week: AI agents explained for beginners, n8n vs Claude Code How to put an AI agent to work this week, drawn start to finish: what an AI agent is, what it's made of, and which tool to build it in. AI agent vs chatbot vs automation: - An automation is a sprinkler on a timer. Six in the morning, every day, same water, even when it's raining. That's a workflow: same trigger, same steps. - A chatbot is a smart friend on the phone. Great advice, but you're still the one under the sink holding the wrench. - An AI agent is the handyman you let into the house. You hand over the job and he does the work, in a loop: goal, plan, act, check, repeat, until the job is done or he needs you. The four pieces of every AI agent you'd trust with real work: 1. The brain: the AI model inside Claude, ChatGPT or Gemini. It reads, reasons and picks the next step. 2. Context: instructions (the job sheet), memory (notes from last time) and knowledge (your price list, services and documents). This is the piece people skip, and it's why their agent writes like a stranger. 3. Tools: the keys you hand over, like your email, calendar and files. Only the keys this job needs. 4. Guardrails: house rules. Anything that leaves the house (an email, a payment, a deletion) waits for your approval. Human in the loop. One real example, end to end. The goal, in one sentence: follow up on today's client call. The AI agent reads the call notes in Google Drive, checks Google Calendar for an open slot (your client notes say she likes mornings), drafts the follow-up email in Gmail with the price sheet linked, and updates your client sheet in Google Sheets. Then it stops, so you can read it and hit send. n8n vs Claude Code, the doorbell and the desk: - n8n is the doorbell: a visual workflow automation tool that connects your apps and waits for a trigger. A call note lands in a Google Drive folder and the follow-up gets drafted, day or night. For the step that needs judgment, the n8n AI Agent node holds the same four pieces and runs the same loop. - Claude Code is the desk: an AI agent that works next to you, on your computer, in your files. It reads CLAUDE.md (the job sheet), uses skills (your steps written down once) and reaches Gmail and your calendar through MCP (the keys). - Doorbell jobs go in n8n: something happens, same steps, every time. Desk jobs go to Claude Code: messy, different every time, or living in your files. They work together, too: n8n has a built-in MCP server, so Claude Code can build n8n workflows for you. How to put an AI agent to work this week: 1. Pick one job you do every week that starts the same way (follow-ups, quote requests, the Monday report). 2. Write the context: one page with the job, how you like it done, and three good examples. 3. Hand it one key, drafts only. It reads and drafts, and nothing sends. 4. Two weeks of yeses. It drafts, you send, and every fix goes into that one page. That's your first agent: one job, one page, one key, two weeks of yeses. The only part left is the setup: n8n, Claude Code, and the keys wired into your real tools. I teach all of it inside my community, course by course, in that order. If you're interested, the link is in my profile. #claudecode #aiagents #n8n #aiautomation

Professor Glitch

18,500 views • 28 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 • 5 months ago

This is getting out of hand: Claude Fable 5.2 can now take any gadget apart from one picture and nobody is talking about it. I gave it one picture of a PS5 controller and got back one that splits open part by part in 24 seconds. What made it work is teardown, a free open-source skill for Claude Code (3,000+ stars on GitHub) that makes Claude build the inside first. Why model a controller by hand for a week when Claude can write every part as code? Here is the workflow: from that one picture Claude writes the motion as math before it draws a single part, so every panel reads the same numbers as the model. It renders a still at every beat and fixes what it finds, then records the tour at 60 fps: the touchpad lifts, both sticks come out on their gimbals, the motor and gears behind L2 and R2 slide out and trigger force jumps from 30% to 78% the second push-back switches on. Step-by-step setup: 1. Install teardown with one npx line 2. Open Claude Code and type /teardown 3. Give it one picture of the thing you want to see inside 4. Let it check every still before it films 5. Record the tour and watch it come apart It runs inside Claude Code, so you'll never keyframe a teardown by hand again. The full guide and every prompt are in the article below.

This is getting out of hand: Claude Fable 5.2 can now take any gadget apart from one picture and nobody is talking about it. I gave it one picture of a PS5 controller and got back one that splits open part by part in 24 seconds. What made it work is teardown, a free open-source skill for Claude Code (3,000+ stars on GitHub) that makes Claude build the inside first. Why model a controller by hand for a week when Claude can write every part as code? Here is the workflow: from that one picture Claude writes the motion as math before it draws a single part, so every panel reads the same numbers as the model. It renders a still at every beat and fixes what it finds, then records the tour at 60 fps: the touchpad lifts, both sticks come out on their gimbals, the motor and gears behind L2 and R2 slide out and trigger force jumps from 30% to 78% the second push-back switches on. Step-by-step setup: 1. Install teardown with one npx line 2. Open Claude Code and type /teardown 3. Give it one picture of the thing you want to see inside 4. Let it check every still before it films 5. Record the tour and watch it come apart It runs inside Claude Code, so you'll never keyframe a teardown by hand again. The full guide and every prompt are in the article below.

Nyxera

35,311 views • 1 day ago

Build your first AI agent with Claude Code (step by step) Most people's first "agent" is a chatbot they have to babysit. This one does a real job: the 40 minutes you lose every morning working out what needs you today. Here's the whole build in Claude Code, in the desktop app and in the terminal: Dump everything on your plate and let Claude find the job that repeats. Let it interview you and write CLAUDE.md, the file it reads every time it starts. Know the difference: an automation repeats steps, an agent decides them. Write the scope: it reads, it never sends, it never deletes. Turn the job into a skill, written down once. Connect only the tools it needs (Gmail and Google Calendar). Set permissions: allow reading, ask before sending, deny deleting. Put it on a schedule, every weekday at 7. Then watch it for a week. When it gets something wrong, fix the skill, not the output. Everything on screen is real Claude Code output on made-up business data. Save this for when you build your first one. #aiagents #aiautomation #claude #aiemployee

Build your first AI agent with Claude Code (step by step) Most people's first "agent" is a chatbot they have to babysit. This one does a real job: the 40 minutes you lose every morning working out what needs you today. Here's the whole build in Claude Code, in the desktop app and in the terminal: Dump everything on your plate and let Claude find the job that repeats. Let it interview you and write CLAUDE.md, the file it reads every time it starts. Know the difference: an automation repeats steps, an agent decides them. Write the scope: it reads, it never sends, it never deletes. Turn the job into a skill, written down once. Connect only the tools it needs (Gmail and Google Calendar). Set permissions: allow reading, ask before sending, deny deleting. Put it on a schedule, every weekday at 7. Then watch it for a week. When it gets something wrong, fix the skill, not the output. Everything on screen is real Claude Code output on made-up business data. Save this for when you build your first one. #aiagents #aiautomation #claude #aiemployee

Professor Glitch

25,600 views • 19 days ago

🚨 SOMEONE LEAKED THE PROMPT THAT MAKES CLAUDE CODE CREATE ITS OWN SKILLS AND WORK BETTER EVERY DAY WITHOUT YOU TOUCHING ANYTHING No programming. Just paste. A single prompt does it all: Time needed: 2 minutes Actions: copy and paste into Claude Code The mistake 90% of people make with Claude: explaining the same thing to it every day. The same tone, the same steps, the same corrections. And the next day it starts from scratch again. → Detects what you repeat: reviews your project and asks you what tasks you do every week → Creates a skill for each one: instructions, templates, and examples that Claude loads only when it needs them → Tests them before giving them to you: runs each skill with a real case and fixes it if it fails → Learns from your corrections: every time you correct something, it updates the skill so it doesn't repeat the error → Zero code: you tell it what you do and Claude builds its own library of skills Before, this meant writing manuals, templates, and processes for weeks. Now it's just Ctrl+V. Save it before they delete it 🔖 Follow Tomcruise AI for more...

🚨 SOMEONE LEAKED THE PROMPT THAT MAKES CLAUDE CODE CREATE ITS OWN SKILLS AND WORK BETTER EVERY DAY WITHOUT YOU TOUCHING ANYTHING No programming. Just paste. A single prompt does it all: Time needed: 2 minutes Actions: copy and paste into Claude Code The mistake 90% of people make with Claude: explaining the same thing to it every day. The same tone, the same steps, the same corrections. And the next day it starts from scratch again. → Detects what you repeat: reviews your project and asks you what tasks you do every week → Creates a skill for each one: instructions, templates, and examples that Claude loads only when it needs them → Tests them before giving them to you: runs each skill with a real case and fixes it if it fails → Learns from your corrections: every time you correct something, it updates the skill so it doesn't repeat the error → Zero code: you tell it what you do and Claude builds its own library of skills Before, this meant writing manuals, templates, and processes for weeks. Now it's just Ctrl+V. Save it before they delete it 🔖 Follow Tomcruise AI for more...

Tomcruise AI

38,809 views • 5 days ago

You can turn any YouTube tutorial into a working Claude Code agent by having two AIs watch it separately. Install bradautomates/claude-video so Claude sees the frames and the transcript. Send the same link to Gemini @googlegemini, which watches it natively. Reconcile both reads into one spec that labels every line confirmed, single source, or conflict. You only check the conflicts. Hand it to skill-creator and it writes the agent. If you're the human: share this reel to Claude Code and watch it build. Comment "Youtube" for my full step-by-step guide. #claudecode #claude #ai #aiagents #aitools

You can turn any YouTube tutorial into a working Claude Code agent by having two AIs watch it separately. Install bradautomates/claude-video so Claude sees the frames and the transcript. Send the same link to Gemini @googlegemini, which watches it natively. Reconcile both reads into one spec that labels every line confirmed, single source, or conflict. You only check the conflicts. Hand it to skill-creator and it writes the agent. If you're the human: share this reel to Claude Code and watch it build. Comment "Youtube" for my full step-by-step guide. #claudecode #claude #ai #aiagents #aitools

Jens Heitmann

162,700 views • 3 months ago

How to build an AI employee inside Claude Code (the whole picture) Most people think an AI employee is some complicated app. Under the hood, it's Claude Code plus a folder of plain text files. Here's the whole picture, using Quill, the employee who runs my Google Workspace. Profile: who she is, what she can do on her own, and when she has to ask first (money, contracts, first-time contacts). Context (CLAUDE.md): the file Claude Code reads first every session. It points her to how I write, who my clients are, and what the business does. Skills (SKILL.md): plain-English playbooks. The name and one-line description tell Claude when to use one; the steps run like a checklist. Tools: connectors give her hands in Gmail, Sheets, Calendar and Drive, through MCP or a small command-line app. Schedule: 9 AM triage, then an approvals check every 30 minutes. Memory: every correction becomes a standing rule she reads before drafting, so my edits get smaller every week. Team: when a new client wants a proposal, Quill hands it to Atlas, gets the PDF back and attaches it to the draft, and it still waits for my approval. Claude Code is the brain that reads all of it. You're the boss who approves. #aiemployee #aiagent #aiautomation #claudecode

Professor Glitch

15,100 views • 1 month ago

How to become the AI person on your team Most people use AI at work like a smarter search bar: paste something in, ask, copy the answer out. Soon that's as common as knowing email. The people getting noticed build with it. They connect AI to the tools their team already uses. Here's one real example, the weekly sales report that eats someone's Monday morning: The doors. Almost every work app (HubSpot, Jira, Google Sheets, Slack) has an API, a door other software can use. No code needed. n8n. Each door becomes a box on a canvas. A schedule trigger fires every Monday at 7, HubSpot pulls last week's deals, Jira counts open tickets, Sheets brings the target, and one AI step has Claude write the report. Context. Give Claude one page about your team: who reads the report, the quarterly target, and that your manager wants bad news first. Now it sounds like your team, not a stranger. Approval. The draft comes to you in Slack first. Tap approve and it posts to the team at 8. Claude Code. For questions that need judgment ("why did the Acme deal slip?"), plug the same tools into Claude Code. It checks HubSpot, Jira and Slack by itself and answers with sources. The rule to keep: if the steps never change, build it in n8n. If the work needs judgment, give it to Claude Code. It takes a few weekends: learn how APIs work, learn one tool all the way down, then connect your first chore. I teach all of it from zero inside my community, seven courses in order. If you're interested, the link is in my profile. #aiautomation #aiagent #n8n #claudecode

Professor Glitch

25,200 views • 1 month ago

Claude Code is now free to run. Most people still think you need a paid setup. Here’s the basic flow: → Install Claude Code with the official installer. → Create a free OpenRouter account. → Grab your API key. → Install Claude Code Router. → Point Claude Code to the local router. → Choose a free model with the :free suffix. → Run CCR code instead of normal Claude Code. → Check /status to confirm it works. You keep the Claude Code workflow. You just route it through a free model.

Claude Code is now free to run. Most people still think you need a paid setup. Here’s the basic flow: → Install Claude Code with the official installer. → Create a free OpenRouter account. → Grab your API key. → Install Claude Code Router. → Point Claude Code to the local router. → Choose a free model with the :free suffix. → Run CCR code instead of normal Claude Code. → Check /status to confirm it works. You keep the Claude Code workflow. You just route it through a free model.

Julian Goldie SEO

17,618 views • 5 months ago

Why your AI gets dumber the longer you chat (context rot): the one Claude Code file, plus one habit, that fixes it How context rot works: 1. Everything in your chat sits in the AI's working memory, the context window: every message, every file it opened, every answer it gave. The model reads through all of it before every reply. 2. Anthropic, the company behind Claude, says the more tokens you pile into the context window, the worse the model gets at recalling any one thing in it. They call it an attention budget, and every new token spends a little of it. 3. When the window fills up, Claude Code compacts: it replaces the conversation with a summary. If a rule only lived in the chat, it can get lost in that summary. The fix is one file, CLAUDE.md, plus one habit. 4. CLAUDE.md is a plain text file in your project folder. Claude Code reads it at the start of every session, and after compaction it re-reads it from the file. Think of it as a sign bolted above the whiteboard: wipe the board all you want, the sign stays. 5. How to create a CLAUDE.md: open Claude Code in your project folder and type /init. It writes a first draft. Then add what it can't guess: who you are, who the client is, and your rules ("never change a headline without asking", "prices come from column D of the Google Sheet", "dates are day, month, year"). 6. Keep CLAUDE.md short. Anthropic's Claude Code guide says to aim for under 200 lines, because a bloated file gets ignored too. For every line, ask: would it make a mistake without this? If not, cut it. The other half of the fix is how you work: 7. One job, one session. Type /clear when you switch jobs: the board's wiped, and the sign (CLAUDE.md) is still up. 8. If you've corrected the AI twice on the same thing, skip round three in capitals. Clear it, put the rule in CLAUDE.md, and start again. This is context engineering for people who don't code: an AI assistant that remembers your business rules, your clients and your formats, for client work, reports, content, spreadsheets and proposals, whether you're a freelancer, an agency or a small business. #claudecode #aiagents #contextengineering #learnai

Why your AI gets dumber the longer you chat (context rot): the one Claude Code file, plus one habit, that fixes it How context rot works: 1. Everything in your chat sits in the AI's working memory, the context window: every message, every file it opened, every answer it gave. The model reads through all of it before every reply. 2. Anthropic, the company behind Claude, says the more tokens you pile into the context window, the worse the model gets at recalling any one thing in it. They call it an attention budget, and every new token spends a little of it. 3. When the window fills up, Claude Code compacts: it replaces the conversation with a summary. If a rule only lived in the chat, it can get lost in that summary. The fix is one file, CLAUDE.md, plus one habit. 4. CLAUDE.md is a plain text file in your project folder. Claude Code reads it at the start of every session, and after compaction it re-reads it from the file. Think of it as a sign bolted above the whiteboard: wipe the board all you want, the sign stays. 5. How to create a CLAUDE.md: open Claude Code in your project folder and type /init. It writes a first draft. Then add what it can't guess: who you are, who the client is, and your rules ("never change a headline without asking", "prices come from column D of the Google Sheet", "dates are day, month, year"). 6. Keep CLAUDE.md short. Anthropic's Claude Code guide says to aim for under 200 lines, because a bloated file gets ignored too. For every line, ask: would it make a mistake without this? If not, cut it. The other half of the fix is how you work: 7. One job, one session. Type /clear when you switch jobs: the board's wiped, and the sign (CLAUDE.md) is still up. 8. If you've corrected the AI twice on the same thing, skip round three in capitals. Clear it, put the rule in CLAUDE.md, and start again. This is context engineering for people who don't code: an AI assistant that remembers your business rules, your clients and your formats, for client work, reports, content, spreadsheets and proposals, whether you're a freelancer, an agency or a small business. #claudecode #aiagents #contextengineering #learnai

Professor Glitch

12,200 views • 28 days ago

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.

MIKE

32,313 views • 3 months ago

MCP explained in one drawing: how your AI gets inside your apps (Claude, n8n, Gmail) Here's how your AI actually gets inside your apps. It's called MCP, and it fits in one drawing. On its own, an AI is a brain in a box. It can talk and think, but it can't open your email or build anything in n8n. It has no hands. 1. The door is the API. Most apps have a door for other software: Gmail has one, GitHub has one, n8n has one. Every door is a different shape, with its own rules and its own key. 2. The plug is MCP. It's one standard shape. On one side is the AI. On the other side is a small program called an MCP server, one per app, and it knows that app's door. The AI plugs in, and the server does the walking through the door. 3. The menu is the list of tools. When the AI plugs in, it sees every tool the app offers, in plain words. Gmail's server offers create a draft, search mail and read a message. n8n's server offers list workflows, create a workflow and test it. The AI reads the list like a menu, picks a tool and calls it. That's how Claude builds a whole workflow inside n8n, node by node, and checks its own work, while you never open n8n. 4. Connecting one takes one sentence. In Claude Code, say: "Connect yourself to my n8n, here's the address and a key I made just for you." Claude writes a small settings file with the server's name and the key. Type /mcp and it says connected. That's the setup for most apps. Some, like Gmail, you just sign in to instead. 5. The key is the important part. An MCP server can only use the tools on its menu, and only as far as its key allows. So make a key that can do the job and nothing more. If the app lets you limit a key, make it read only when reading is all you need. If it doesn't, use a test account. And if a key ever leaks, cancel it inside the app. One click, and nobody can use it, the AI included. One honest line: MCP doesn't make the AI smarter. It gives a smart thing a way to act, and everything it does through that plug, it does as you. So you still check the work, like you would a new hire's. If you're starting from scratch, I have step-by-step lessons for all of this inside my community. There are eight courses, in order, from the basics of AI to automations, building websites and apps, and AI agents. If you're interested, the link is in my profile. #mcp #cli ##aiagents #aiautomation #claudecode

Professor Glitch

18,500 views • 26 days ago

/harness A Claude Code plugin built for Fable 5. It runs your agent against your project, watches it break, and writes a CLAUDE. md from the actual failures. It catches wrong paths, missing scripts, and bad assumptions so your agent never hits the same wall twice ↓

/harness A Claude Code plugin built for Fable 5. It runs your agent against your project, watches it break, and writes a CLAUDE. md from the actual failures. It catches wrong paths, missing scripts, and bad assumptions so your agent never hits the same wall twice ↓

Hyperbrowser

78,754 views • 5 months ago

Claude Code + computer use is f*cking cracked 🤯 Build a landing page → Claude opens Chrome, looks at it, spots every issue, and fixes it — without you describing a single thing. All inside Claude Code. Perfect for DTC brands and agencies who are still vibe-coding landing pages and advertorials in Claude Code, then manually opening them in Chrome, spotting 15 things wrong, and describing every visual issue back to Claude one at a time. If you're building pages in Claude Code and your workflow looks like this — build the page, open it in Chrome, spot broken spacing, go back to Claude, type "the CTA button is too low and the hero image is cut off," wait for the fix, open Chrome again, find 3 new issues, describe those too ... Claude Code + computer use eliminates the entire loop: → Claude writes the full landing page or advertorial → Opens Chrome and navigates to it → Spots layout issues, broken spacing, off-brand colors, missing elements → Fixes everything and re-checks until the page looks right → Tests your Shopify product pages by clicking through like a real customer → Walks through your checkout flow and flags friction before customers hit it → You only see the finished, visually verified result No describing what you see on screen. No "the CTA button needs more contrast" back-and-forth. No being the eyeballs for an AI that can't see. What you get: → Landing pages and advertorials Claude builds AND visually QAs before you ever look at them → Product pages Claude clicks through — testing layout, images, and CTAs like a real user → HTML dashboards Claude opens and verifies the charts actually render → Checkout flows Claude walks through step by step to catch friction → All of it happening in one session — build, test, fix, done One prompt. Claude builds it, checks it, and fixes it. You just review the finished page. I put together a full playbook with the exact setup, the prompts, and 5 DTC workflows that use Claude Code + computer use. Want it for free? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

Mike Futia

19,274 views • 7 months ago

I created a skill for OpenClaw to use Claude Code It launches a CRON that checks background tasks every minute When done it wakes up the main thread Insane result: I can code on my project while working out and launch 10 Claude Code agents on the same project

I created a skill for OpenClaw to use Claude Code It launches a CRON that checks background tasks every minute When done it wakes up the main thread Insane result: I can code on my project while working out and launch 10 Claude Code agents on the same project

Melvyn • Builder

36,400 views • 9 months ago

$THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this$

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,568 views • 5 months ago

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: never let build logs touch your main session. One tiny agent runs the build and hands back 3 lines. Same build, two ways: inline it is 40k tokens and $0.09 every single run. Through the builder it is 3 lines and nothing. You just launch Claude Code like this: claude --model sonnet # builder.md: model: haiku here's the split: → Sonnet 5.5 edits code in the main session and never sees a log → a Haiku 5.5 builder runs npm build, tsc and the test suite → it reads all 2k log lines, 227 files and 18 tests itself → it returns 3 lines: what ran, what failed, where the part everyone gets wrong: they run the build in the main session. 40k tokens of log noise per run, and every later message in that session carries it. you pay for that log again on every turn until the context resets. the builder agent is 10 lines of markdown. name, model haiku, tools Bash, and one rule: run the build, fix nothing, return 3 lines. that "fix nothing" is the whole trick. the cheap agent never tries to be clever, it just reports, and the lead decides what to do. one catch worth knowing: past 100k of context Haiku jumps to 5x its own price, so the builder is kept deliberately small. main context grows by +0 instead of +40k. that is the entire win. Sonnet edits. Haiku builds. The log never leaves the agent. JEV engineering is the same move one layer down: 1,301 forks this run - which agent, retry or stop, fix or report - resolved in code at 0.90 sharpness, and only the split ones ever reach Sonnet the full tree ▸ Sonnet 5.5 runs the main session and edits code only ▸ a Haiku 5.5 builder agent runs build, typecheck and tests ▸ the builder reads every log line and returns 3 lines, never the log ▸ the builder fixes nothing, it only reports ▸ Sonnet 5.5 reads those 3 lines and decides the next edit ▸ JEV resolves micro-forks in code and escalates only the split ones paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Sonnet 5.5 for editing code only. 2. Create a builder subagent with model: haiku and tools: Bash. 3. The builder runs build, typecheck and tests, reads all output itself, and returns at most 3 lines: what ran, what failed, where. 4. The builder never fixes anything, it only reports. 5. Add one rule to CLAUDE.md: build output never enters the main session, no exceptions. 6. Route deterministic forks (which agent, retry or stop, fix or report) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: never let build logs touch your main session. One tiny agent runs the build and hands back 3 lines. Same build, two ways: inline it is 40k tokens and $0.09 every single run. Through the builder it is 3 lines and nothing. You just launch Claude Code like this: claude --model sonnet # builder.md: model: haiku here's the split: → Sonnet 5.5 edits code in the main session and never sees a log → a Haiku 5.5 builder runs npm build, tsc and the test suite → it reads all 2k log lines, 227 files and 18 tests itself → it returns 3 lines: what ran, what failed, where the part everyone gets wrong: they run the build in the main session. 40k tokens of log noise per run, and every later message in that session carries it. you pay for that log again on every turn until the context resets. the builder agent is 10 lines of markdown. name, model haiku, tools Bash, and one rule: run the build, fix nothing, return 3 lines. that "fix nothing" is the whole trick. the cheap agent never tries to be clever, it just reports, and the lead decides what to do. one catch worth knowing: past 100k of context Haiku jumps to 5x its own price, so the builder is kept deliberately small. main context grows by +0 instead of +40k. that is the entire win. Sonnet edits. Haiku builds. The log never leaves the agent. JEV engineering is the same move one layer down: 1,301 forks this run - which agent, retry or stop, fix or report - resolved in code at 0.90 sharpness, and only the split ones ever reach Sonnet the full tree ▸ Sonnet 5.5 runs the main session and edits code only ▸ a Haiku 5.5 builder agent runs build, typecheck and tests ▸ the builder reads every log line and returns 3 lines, never the log ▸ the builder fixes nothing, it only reports ▸ Sonnet 5.5 reads those 3 lines and decides the next edit ▸ JEV resolves micro-forks in code and escalates only the split ones paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Sonnet 5.5 for editing code only. 2. Create a builder subagent with model: haiku and tools: Bash. 3. The builder runs build, typecheck and tests, reads all output itself, and returns at most 3 lines: what ran, what failed, where. 4. The builder never fixes anything, it only reports. 5. Add one rule to CLAUDE.md: build output never enters the main session, no exceptions. 6. Route deterministic forks (which agent, retry or stop, fix or report) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

Sprytix

11,275 views • 20 days ago

SOMEONE ON THE CLAUDE CODE TEAM JUST EXPLAINED HOW TO MAKE A TASK RUN THE SAME WAY EVERY TIME Lydia Hallie uses dynamic workflows for any task she wants to rerun the same way. No need for hundreds of subagents: around 10 is enough for her. Two types of people will see this: Person 1: explains the same task to Claude every week and gets something different every time. Person 2: turns it into a workflow and reruns it with one command. How it works: → Ask Claude to "make a workflow that does X" → Claude writes the file, plain JavaScript you can edit → You decide which subagents run and in what order → Save it from /workflows → Rerun it anytime with /name A skill tells Claude how to do something. A workflow tells it exactly in what order. Save this 🔖

SOMEONE ON THE CLAUDE CODE TEAM JUST EXPLAINED HOW TO MAKE A TASK RUN THE SAME WAY EVERY TIME Lydia Hallie uses dynamic workflows for any task she wants to rerun the same way. No need for hundreds of subagents: around 10 is enough for her. Two types of people will see this: Person 1: explains the same task to Claude every week and gets something different every time. Person 2: turns it into a workflow and reruns it with one command. How it works: → Ask Claude to "make a workflow that does X" → Claude writes the file, plain JavaScript you can edit → You decide which subagents run and in what order → Save it from /workflows → Rerun it anytime with /name A skill tells Claude how to do something. A workflow tells it exactly in what order. Save this 🔖

Dean W. Perkins

40,141 views • 10 days ago