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.

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc... show more

Ian Nuttall

76,620 subscribers

117,186 views • 1 year ago •via X (Twitter)

Education Finance Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Ian Nuttall1 year ago

blown away by the content quality:

Ian Nuttall1 year ago

also worth noting it still hallucinates stuff this is not a real package! some work to do and maybe need to add a firecrawl mcp or build a data for seo one to get more accurate info but the content itself is exactly the type of writing i would want on my blog

Ian Nuttall1 year ago

second attempt with at least 50% less hallucinations (maybe?)

eSignatures.com1 year ago

Add secure, embedded signing to your WordPress site in seconds. Try now!

Jay Guthrie1 year ago

since we not getting to 1 million I am releasing it for you all

micah rich1 year ago

What if I open it one million timesssss, the curiosity is killing me

Abdelmoghit1 year ago

this is wild feels like we’re finally hitting that “infinite content machine” moment for real drop the prompt when u ready king, we waiting

Chris Sev1 year ago

come on 1 million 🤞

Jeffrey Behnke 💻1 year ago

Put a content length limit, then start a new chat to finish. It will probably hallucinate less.

Falkon Ready1 year ago

@grok remind me in 7 days

The GTM Marketer1 year ago

How is the research done? Is there a database for the research?

Related Videos

UGC Agent An AI agent that generates video content end-to-end using x402 micropayments and Vercel's Workflow Kit You give it a topic. It researches, writes a script, and creates the video, paying for every tool it needs along the way Here's how it works 🧵👇

UGC Agent An AI agent that generates video content end-to-end using x402 micropayments and Vercel's Workflow Kit You give it a topic. It researches, writes a script, and creates the video, paying for every tool it needs along the way Here's how it works 🧵👇

Ash

12,456 views • 8 months ago

I just built a content engine in Claude Code that writes blog posts in your brand's exact voice 🤯 One Claude plugin runs the whole content workflow: brand voice, research, writing, AI-slop scoring, and repurposing into social. It writes in YOUR voice, refuses to fabricate stats, and scores every draft 0-100. All inside Claude Code. So I pointed it at Grüns, one of the sharpest DTC brands out there. I fed it their homepage. In seconds it built a brand-voice profile, their playful anti-hype tone, the "Rip. Tip. Enjoy." cadence, the AG1-switcher audience, the 4.8★/100k-review proof. Then I asked for one post: "why your gut health controls your skin, hair, and energy." It came back publish-ready and scored 89/100 on the first pass: → Answer-first, with question headings AI engines can quote → Zero AI-slop phrases (no "unlock," no "in today's fast-paced world") → And it refused to invent a single stat, the fastest way to get a supplement brand demoted It sounded like Grüns wrote it, not ChatGPT. Perfect for e-comm operators and agencies who are sick of AI tools that all sound identical, $300 freelance posts that still need a rewrite, and content that reads like the slop Google now punishes. So I put together the full playbook to build your own. The complete guide to building this content engine in Claude Code: branded to you, tuned to your voice, repeatable across every client. The kind of post you'd pay a freelancer $300 for, written in minutes, in the brand's actual voice. What's inside: → The architecture (orchestrator + writer/editor/researcher agents) → How to capture any brand's voice into a reusable profile → The 0-100 scoring + AI-slop detection framework → The one-post-to-a-week-of-social repurposing loop → The full build, start to finish Want the playbook for free? > Like this post > Comment "CONTENT" And I'll send it over (must be following so I can DM)

Mike Futia

23,764 views • 2 months ago

Stop bookmarking posts or tutorials you'll never implement. I made a Chrome extension that sends any URL or X post to OpenCode. It reads the content, researches, implements the key examples, runs tests, and writes a report. One click. Working code. Turn your ADHD into superpowers It's free. Link below

Stop bookmarking posts or tutorials you'll never implement. I made a Chrome extension that sends any URL or X post to OpenCode. It reads the content, researches, implements the key examples, runs tests, and writes a report. One click. Working code. Turn your ADHD into superpowers It's free. Link below

BowTiedSwan | SaaS, Web3 & Data Science Magician

123,499 views • 7 months ago

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

leopardracer

247,908 views • 1 month ago

open Claude Code type a prompt. one model does everything. congrats, you just used 20% of it meanwhile I built 30 sub-agents one reviews my code before commit one finds bugs and writes the patch one drafts cold emails from one line one triages my inbox before I wake up one logs every decision so future me knows why each agent = one markdown file in .claude/agents/ most Claude Code users don't even know this exists. all 30 files in the article. ready to copy. the article has every file. every prompt. just copy and run.

open Claude Code type a prompt. one model does everything. congrats, you just used 20% of it meanwhile I built 30 sub-agents one reviews my code before commit one finds bugs and writes the patch one drafts cold emails from one line one triages my inbox before I wake up one logs every decision so future me knows why each agent = one markdown file in .claude/agents/ most Claude Code users don't even know this exists. all 30 files in the article. ready to copy. the article has every file. every prompt. just copy and run.

Nav Toor

71,467 views • 3 months ago

Introducing --agent flag in CodeRabbit CLI 🎉 The new --agent flag turns CodeRabbit into a tool your AI agent can use, providing structured JSON output instead of terminal text. Your agent writes code, CodeRabbit reviews it, reads the JSON, and fixes what's flagged.

Introducing --agent flag in CodeRabbit CLI 🎉 The new --agent flag turns CodeRabbit into a tool your AI agent can use, providing structured JSON output instead of terminal text. Your agent writes code, CodeRabbit reviews it, reads the JSON, and fixes what's flagged.

CodeRabbit

22,404 views • 4 months ago

THIS GUY REPLACED HIS ENTIRE CONTENT TEAM WITH A FREE AI AGENT - NOW GETS 340K VIEWS PER POST ALONE 😳 he uses hermes + obsidian and it's completely free - runs on the claude plan he already had you give it one idea and it splits into a team one part researches, one finds the angle, one writes the post, one turns it into a newsletter, one makes the captions all of that from a single sentence it already knows his voice, his audience, his business - so nothing it makes sounds generic he doesn't manage it, remind it, or babysit it 7,100 bookmarks, 340K views, 20 minutes per post, zero team, zero paid tools ↓ he wrote the full guide so you can copy the exact setup from zero:

THIS GUY REPLACED HIS ENTIRE CONTENT TEAM WITH A FREE AI AGENT - NOW GETS 340K VIEWS PER POST ALONE 😳 he uses hermes + obsidian and it's completely free - runs on the claude plan he already had you give it one idea and it splits into a team one part researches, one finds the angle, one writes the post, one turns it into a newsletter, one makes the captions all of that from a single sentence it already knows his voice, his audience, his business - so nothing it makes sounds generic he doesn't manage it, remind it, or babysit it 7,100 bookmarks, 340K views, 20 minutes per post, zero team, zero paid tools ↓ he wrote the full guide so you can copy the exact setup from zero:

Isra

25,704 views • 1 month ago

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Mnimiy

113,663 views • 2 months ago

Kicking off the week with a spotlight on an agent every dev will love: one that writes and publishes your technical blogs for you. Meet (DEV Community) Writer Agent on ASI:One. ⚡ Give it a topic, your username, and API key: and it auto-writes + publishes full technical blog posts with code, tags, and structure. No hassle. Built with uAgents. Powered by Try now: Link to Agent: Watch 👇

Kicking off the week with a spotlight on an agent every dev will love: one that writes and publishes your technical blogs for you. Meet (DEV Community) Writer Agent on ASI:One. ⚡ Give it a topic, your username, and API key: and it auto-writes + publishes full technical blog posts with code, tags, and structure. No hassle. Built with uAgents. Powered by Try now: Link to Agent: Watch 👇

Fetch.ai

14,280 views • 1 year ago

Your Claude has a tell, and almost nobody uses it. Make it start every reply with your name. One line in custom instructions, no code. The moment it stops saying your name, its context window is full. That is the exact point the output starts drifting, and you do not notice. Name stops? Start a fresh chat. It has killed about 90% of my “why has Claude gone weird” moments. Miners sent a canary down the pit to catch the gas they could not see. Same trick, for your context. Comment GUIDE and I’ll send you the exact canary setup.

Your Claude has a tell, and almost nobody uses it. Make it start every reply with your name. One line in custom instructions, no code. The moment it stops saying your name, its context window is full. That is the exact point the output starts drifting, and you do not notice. Name stops? Start a fresh chat. It has killed about 90% of my “why has Claude gone weird” moments. Miners sent a canary down the pit to catch the gas they could not see. Same trick, for your context. Comment GUIDE and I’ll send you the exact canary setup.

Charlie Hills

24,120 views • 1 month ago

I just vibe-coded a complete SEO Agency In a Box with Claude Code. One keyword in → full research, competitor analysis, SEO-optimized article, metadata, and AI graphics out. All on auto-pilot. Perfect for SEO agencies and DTC brands who are tired of spending an entire day producing a single piece of SEO content. Creating quality SEO content is a huge pain. You're reading competitor articles one by one, trying to find content gaps, writing drafts from scratch, then going back to optimize everything before you even think about graphics or metadata. This vibe-coded tool solves it: → Set up your brand once (value prop, tone of voice, writing samples) → Enter a topic and keywords → SERP API + Firecrawl scrape and analyze the top-ranking competitors → Gemini generates a full research plan with intent, gaps, and strategic positioning → Claude writes the article based on your brand guidelines and the research → Nano Banana Pro generates thumbnail and in-blog images → SEO metadata (title, description, slug) created automatically What this outputs: - Full competitive research and content brief - SEO-optimized articles with internal links and proper formatting - AI-generated images and thumbnail - Meta title, description, and slugs - Batch mode for multiple articles at once - Content rewrite mode for existing URLs that aren't ranking - LinkedIn and X repurposing built in Built 100% in Claude Code. (I'm giving away the prompts) I recorded a full walkthrough showing exactly how every part of this works, and I'm including ALL of the prompts I used for Claude Code. Want access for free? > Like this post > Comment "SEO" And I'll send it over (must be following so I can DM)

Mike Futia

68,585 views • 6 months ago

Claude Code creator: "100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too. The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops" in this interview he breaks down exactly how a system changes everything: - the memory and context features that turn Claude into a second brain - the knowledge architecture most users don't know Claude can build - the integration layer that connects Claude to your actual workflow - why typing one question at a time is the most expensive way to use Claude if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed full guide in the article below

Claude Code creator: "100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too. The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops" in this interview he breaks down exactly how a system changes everything: - the memory and context features that turn Claude into a second brain - the knowledge architecture most users don't know Claude can build - the integration layer that connects Claude to your actual workflow - why typing one question at a time is the most expensive way to use Claude if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed full guide in the article below

Khairallah AL-Awady

39,292 views • 2 months ago

shipped this incredible AI Agent in PostSyncer 🤓 it generates posts from pretty much anything: • upload an image → AI creates the post • paste a link → AI analyzes and writes • drop a PDF → AI extracts insights • share an article → AI crafts the copy so many possibilities the AI does a crazy good job at analyzing and creating content from whatever you throw at it it even created this post, THAT'S SOOO META 🤯 PostSyncer is becoming the best social media tool out there

shipped this incredible AI Agent in PostSyncer 🤓 it generates posts from pretty much anything: • upload an image → AI creates the post • paste a link → AI analyzes and writes • drop a PDF → AI extracts insights • share an article → AI crafts the copy so many possibilities the AI does a crazy good job at analyzing and creating content from whatever you throw at it it even created this post, THAT'S SOOO META 🤯 PostSyncer is becoming the best social media tool out there

Tibo

12,537 views • 8 months ago

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." this is one of the best workflows I've seen in a long time in this video she breaks down exactly how most people are using Claude: - the 14% you lose to CLAUDE.md before typing a word - the automation workflows most users don't know exist - the daily task pipelines that run without touching the keyboard - the daily workflows Anthropic's own engineers automated first if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." this is one of the best workflows I've seen in a long time in this video she breaks down exactly how most people are using Claude: - the 14% you lose to CLAUDE.md before typing a word - the automation workflows most users don't know exist - the daily task pipelines that run without touching the keyboard - the daily workflows Anthropic's own engineers automated first if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Khairallah AL-Awady

920,550 views • 2 months ago

Claude Opus 4.7 + YouTube Research = SEO Gold AI slop will kill your SEO. YouTube content arbitrage will save it. I built a Claude prompt that finds topics where the top videos cover the answer in depth, but the ranking blog posts barely scratch it. You write the page that should have ranked all along. Reply "prompt" and I'll send it.

Claude Opus 4.7 + YouTube Research = SEO Gold AI slop will kill your SEO. YouTube content arbitrage will save it. I built a Claude prompt that finds topics where the top videos cover the answer in depth, but the ranking blog posts barely scratch it. You write the page that should have ranked all along. Reply "prompt" and I'll send it.

borja

18,876 views • 3 months ago

DELETE FIGMA. ONE MCP CONNECTOR TURNS CLAUDE CODE INTO A GOD-MODE STUDIO IN 30 MINUTES. The exact setup, step by step, no jokes: > open connectors, add a custom connector, drop in the Higgsfield MCP > open a Claude Code session and paste one prompt > it generates the first frame, the last frame, and the motion between them > then wires the result straight into an animated hero section for your site > 30 minutes end to end, nothing rendered by hand The bigger thing hiding here: MCP means the model rents hands. it doesn't know how to animate, so it hires a tool that does, mid-task, without you switching tabs. The ceiling of what one prompt ships isn't the model anymore, it's how many hands you've plugged into it. The method underneath (the goal, the rules, the bar, the loop) is in the article below, and it works with any connector you add next.

DELETE FIGMA. ONE MCP CONNECTOR TURNS CLAUDE CODE INTO A GOD-MODE STUDIO IN 30 MINUTES. The exact setup, step by step, no jokes: > open connectors, add a custom connector, drop in the Higgsfield MCP > open a Claude Code session and paste one prompt > it generates the first frame, the last frame, and the motion between them > then wires the result straight into an animated hero section for your site > 30 minutes end to end, nothing rendered by hand The bigger thing hiding here: MCP means the model rents hands. it doesn't know how to animate, so it hires a tool that does, mid-task, without you switching tabs. The ceiling of what one prompt ships isn't the model anymore, it's how many hands you've plugged into it. The method underneath (the goal, the rules, the bar, the loop) is in the article below, and it works with any connector you add next.

Miraqle

38,373 views • 29 days ago

YOUR AI IS FORGETTING EVERYTHING YOU TAUGHT IT YESTERDAY. That is why most outputs still feel generic. The people getting real leverage in 2026 fixed this with one setup: Obsidian + Claude Code. Obsidian stores your thinking. Claude Code reads the patterns. Your notes become permanent context the agent can access anytime: Daily thoughts. Projects. Ideas. Contradictions. Questions you keep returning to. Then the real unlock: Custom slash commands. `/context` loads your recent thinking instantly. `/emerge` finds hidden ideas across your notes. `/challenge` tests your beliefs against your past writing. `/trace` maps how your thinking evolved over time. One critical rule: The AI never writes to the vault. You write. The agent reads. That is what keeps the system valuable. At first it feels like note-taking. Eventually it feels like a second brain.

YOUR AI IS FORGETTING EVERYTHING YOU TAUGHT IT YESTERDAY. That is why most outputs still feel generic. The people getting real leverage in 2026 fixed this with one setup: Obsidian + Claude Code. Obsidian stores your thinking. Claude Code reads the patterns. Your notes become permanent context the agent can access anytime: Daily thoughts. Projects. Ideas. Contradictions. Questions you keep returning to. Then the real unlock: Custom slash commands. `/context` loads your recent thinking instantly. `/emerge` finds hidden ideas across your notes. `/challenge` tests your beliefs against your past writing. `/trace` maps how your thinking evolved over time. One critical rule: The AI never writes to the vault. You write. The agent reads. That is what keeps the system valuable. At first it feels like note-taking. Eventually it feels like a second brain.

Dami-Defi

41,299 views • 2 months ago

Anthropic Managed Agents team: "Fable 5 is our best model for running self-improving agent systems. Add /loops, dynamic workflows, dreaming and you are unstoppable" in this video he breaks down exactly how most people are using Claude: - the 34% you lose to CLAUDE.md before typing a word - one agent researching. one building. one reviewing. one orchestrating - the architecture that separates hobbyists from real builders - the 3 properties every agent team needs to actually survive if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Anthropic Managed Agents team: "Fable 5 is our best model for running self-improving agent systems. Add /loops, dynamic workflows, dreaming and you are unstoppable" in this video he breaks down exactly how most people are using Claude: - the 34% you lose to CLAUDE.md before typing a word - one agent researching. one building. one reviewing. one orchestrating - the architecture that separates hobbyists from real builders - the 3 properties every agent team needs to actually survive if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Khairallah AL-Awady

21,533 views • 2 months ago

i genuinely can't understand why this isn't the first thing every claude user builds... anthropic quietly shipped a folder system where claude loads specialized instructions on its own based on what you ask. no prompt engineering after setup. almost nobody uses it here's how it actually works... you drop a folder into your skills directory. inside: a SKILL.md that says "trigger this when the user asks about X". claude reads the description once at startup. next time you ask about X, it silently pulls in the whole skill - custom instructions, scripts, examples - like a specialist walking into the room 1. skill for your writing voice - loads only when you draft, never when you analyze 2. skill for your codebase conventions - loads only when you edit that repo, not others 3. skill for your accounting flow - loads only when you say invoice, receipt, or expense your context window stays empty until you need it. one claude behaves like 30 different specialists in one chat and you never manage the switching full breakdown in the article below i test things like this on myself and share the results. follow kai if you want to see what's next

i genuinely can't understand why this isn't the first thing every claude user builds... anthropic quietly shipped a folder system where claude loads specialized instructions on its own based on what you ask. no prompt engineering after setup. almost nobody uses it here's how it actually works... you drop a folder into your skills directory. inside: a SKILL.md that says "trigger this when the user asks about X". claude reads the description once at startup. next time you ask about X, it silently pulls in the whole skill - custom instructions, scripts, examples - like a specialist walking into the room 1. skill for your writing voice - loads only when you draft, never when you analyze 2. skill for your codebase conventions - loads only when you edit that repo, not others 3. skill for your accounting flow - loads only when you say invoice, receipt, or expense your context window stays empty until you need it. one claude behaves like 30 different specialists in one chat and you never manage the switching full breakdown in the article below i test things like this on myself and share the results. follow kai if you want to see what's next

kai

69,978 views • 12 days ago