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.

> be Anthropic engineer > Lydia Hallie > you work on Claude Code, the tool millions use > and you watch almost all of them use it like a search bar > prompt, answer, prompt, answer. 10% of what it can do. > no agents, no caching, no subagents,... show more

Kirill

42,426 subscribers

149,769 views • 1 day ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

- you open Claude Code - fix a bug - close the terminal - tomorrow, same thing - one prompt, one answer, done - you see someone running 10 agents in parallel shipping code while they sleep - "must be a different tool" - then you come across this article - you weren't even using 10% of it - you copy Shopify's exact config - you set up your first agent team - you go to sleep - 3 PRs are ready by morning

- you open Claude Code - fix a bug - close the terminal - tomorrow, same thing - one prompt, one answer, done - you see someone running 10 agents in parallel shipping code while they sleep - "must be a different tool" - then you come across this article - you weren't even using 10% of it - you copy Shopify's exact config - you set up your first agent team - you go to sleep - 3 PRs are ready by morning

darkzodchi

491,494 views • 4 months ago

Holy moly. 🤯 Jack Dorsey just gave away, for free, a full toolkit for running a company where AI agents work right next to your human team. His company Block put it on GitHub. It's already past 29,000 stars. Here's how you set it up takes about 5 minutes: 1. Copy (clone) the code from GitHub. 2. Run your own server. This is where your chats, search, code, and automatic tasks all live. 3. Add your AI agent into a chat channel, just like adding a new team member. Tell it what it's allowed to do, and let it work with your team live. No fees. No middleman. Just you, your team, and your AI agents all in one place you control. This might be what running a business looks like from now on Worth saving.

Holy moly. 🤯 Jack Dorsey just gave away, for free, a full toolkit for running a company where AI agents work right next to your human team. His company Block put it on GitHub. It's already past 29,000 stars. Here's how you set it up takes about 5 minutes: 1. Copy (clone) the code from GitHub. 2. Run your own server. This is where your chats, search, code, and automatic tasks all live. 3. Add your AI agent into a chat channel, just like adding a new team member. Tell it what it's allowed to do, and let it work with your team live. No fees. No middleman. Just you, your team, and your AI agents all in one place you control. This might be what running a business looks like from now on Worth saving.

Charlie Hills

14,039 views • 20 days ago

Most agents can build apps. Cloudflare OS can actually use the apps it builds. This means if your team builds a tool to do a job, an agent can use the tool as you would—on a schedule or upon a triggering event—even if you're not there to work with it.

Most agents can build apps. Cloudflare OS can actually use the apps it builds. This means if your team builds a tool to do a job, an agent can use the tool as you would—on a schedule or upon a triggering event—even if you're not there to work with it.

Phillip Jones

14,552 views • 1 month ago

claude opus 5 runs six agents selling services to local businesses 24/7 and it built a live earth to watch it all happen on here's what it does: - picks a city and pulls a whole niche off google maps - six agents, each hunting one flaw: no website, no socials, no ads, no booking, ignored reviews, dead phone line - whichever agent finds the worst problem claims that business, so no owner gets pitched six times about six different things - writes them a real website off their own reviews from scratch - makes the matching social post and the tap card for the counter - prints a postcard and sends it to their address - then puts a light on the globe so i can watch it land reply "PROMPT" + RT and i'll send you the prompt so you can build this too (must be following so i can DM you)

claude opus 5 runs six agents selling services to local businesses 24/7 and it built a live earth to watch it all happen on here's what it does: - picks a city and pulls a whole niche off google maps - six agents, each hunting one flaw: no website, no socials, no ads, no booking, ignored reviews, dead phone line - whichever agent finds the worst problem claims that business, so no owner gets pitched six times about six different things - writes them a real website off their own reviews from scratch - makes the matching social post and the tap card for the counter - prints a postcard and sends it to their address - then puts a light on the globe so i can watch it land reply "PROMPT" + RT and i'll send you the prompt so you can build this too (must be following so i can DM you)

Chris

83,481 views • 2 months ago

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Money

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Money

Kirill

416,606 views • 3 months ago

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

12,884 views • 4 months ago

ONE PROMPT WON'T MAKE YOU RICH👀 It won’t change your life overnight. And it won’t solve all your problems. But the right prompt can do something much more important. It can reveal things you hadn’t noticed before. Most people use AI to find answers. But the most useful prompts work differently. They make you ask yourself questions. > What’s really holding you back? > What decisions have you been putting off for months? > What are you wasting your time on, convincing yourself it’s important? Sometimes, one honest answer is more valuable than a hundred motivational videos and dozens of books. That’s exactly why I liked this prompt. It doesn’t try to impress with complexity. It helps you see your situation from the outside. Spend a few minutes on it. Perhaps a single conversation with AI will give you more clarity than you expect.

ONE PROMPT WON'T MAKE YOU RICH👀 It won’t change your life overnight. And it won’t solve all your problems. But the right prompt can do something much more important. It can reveal things you hadn’t noticed before. Most people use AI to find answers. But the most useful prompts work differently. They make you ask yourself questions. > What’s really holding you back? > What decisions have you been putting off for months? > What are you wasting your time on, convincing yourself it’s important? Sometimes, one honest answer is more valuable than a hundred motivational videos and dozens of books. That’s exactly why I liked this prompt. It doesn’t try to impress with complexity. It helps you see your situation from the outside. Spend a few minutes on it. Perhaps a single conversation with AI will give you more clarity than you expect.

kozh ./

24,214 views • 3 months ago

Claude Code Agent Teams are f*cking ridiculous 🤯 One prompt → a team lead breaks your project into pieces, spins up multiple AI agents, and they all work on different parts simultaneously. Research, builds, reviews, and debugging: all happening at the same time. All inside Claude Code. If you're running complex projects where every step waits on the last one... Agent teams eliminate the entire bottleneck: → Tell Claude what you need and describe the team structure in plain English → A lead agent breaks the work into a shared task list → It spawns 3-5 teammates — each with their own context and workspace → Teammates research, build, test, and review in parallel → They message each other, share findings, and challenge each other's work → The lead synthesizes everything into a finished deliverable No managing agents yourself. No waiting for step 1 to finish before step 2 starts. No single-lens reviews that miss half the issues. What you get: → Competitive research across 5 brands done in minutes instead of hours → Multi-component builds where frontend, backend, and data layers happen simultaneously → Creative reviews from 3 different angles at once — brand voice, conversion, differentiation → Funnel debugging where 4 agents investigate 4 theories and debate until they find the real answer Built 100% in Claude Code with one settings change. I put together a full DTC playbook: 5 workflows with copy-paste prompts, the exact setup process, token management tips, and honest guidance on when agent teams are worth it vs. when a simpler approach is the better move. Want it for free? > Like this post > Comment "AGENTS" And I'll send it over (must be following so I can DM)

Mike Futia

46,519 views • 7 months ago

You're still typing every turn The guy who built the tool wrote the loop that types them for him "I don't prompt Claude anymore I write loops that prompt Claude" A loop takes four shapes turn-based, you close it each round goal-based - all tests pass, stop after 5 tries time-based - every 10 min, fix what's red, overnight proactive - CI breaks, agents fix it and open a PR, no human at all A judge closes the loop, not you The prompt was never the unit of work the loop is Full breakdown below

You're still typing every turn The guy who built the tool wrote the loop that types them for him "I don't prompt Claude anymore I write loops that prompt Claude" A loop takes four shapes turn-based, you close it each round goal-based - all tests pass, stop after 5 tries time-based - every 10 min, fix what's red, overnight proactive - CI breaks, agents fix it and open a PR, no human at all A judge closes the loop, not you The prompt was never the unit of work the loop is Full breakdown below

Skaly_Bull

12,558 views • 1 month ago

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING OPUS 5 This is the most important prompting guide for anyone using Claude. Bookmark this before you forget. Most people still prompt Opus 5 like older models. That's the mistake. > give the complete task upfront — don't drip-feed instructions. > explicitly ask for shorter responses if you want them. > use low/medium effort by default. increase effort only when needed. > let it finish the entire feature instead of asking for partial implementations. > use subagents intentionally for large codebases, not every task. Opus 5 is at its best when you stop micromanaging it and let it own the work. Read it before writing your next prompt. Claude → Opus 5 → Agentic Execution → Production-Ready Output → Money

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING OPUS 5 This is the most important prompting guide for anyone using Claude. Bookmark this before you forget. Most people still prompt Opus 5 like older models. That's the mistake. > give the complete task upfront — don't drip-feed instructions. > explicitly ask for shorter responses if you want them. > use low/medium effort by default. increase effort only when needed. > let it finish the entire feature instead of asking for partial implementations. > use subagents intentionally for large codebases, not every task. Opus 5 is at its best when you stop micromanaging it and let it own the work. Read it before writing your next prompt. Claude → Opus 5 → Agentic Execution → Production-Ready Output → Money

Rahul

407,371 views • 2 months ago

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

BuBBliK

200,690 views • 4 months ago

If you're building an agentic workspace, your nav has a job normal navs don't The job: - Agents run async, out of sight, so the UI has to prove work is happening - No modals or stuff like that, just ambient signal in a bar people already watch Show the work: - The Agents icon wears a live ring the moment an agent picks up a task - It fires in real bursts, then rests, so it reads like a teammate instead like a spinner stuck on What's it doing: - Hover mid task and the state goes live: Writing code… Running tests… Reading docs… - Status sits on the icon, not buried three clicks deep Why it matters: - Trust in agents comes from knowing they're alive and working - Bake that into the nav and every screen you ship gets it for free

If you're building an agentic workspace, your nav has a job normal navs don't The job: - Agents run async, out of sight, so the UI has to prove work is happening - No modals or stuff like that, just ambient signal in a bar people already watch Show the work: - The Agents icon wears a live ring the moment an agent picks up a task - It fires in real bursts, then rests, so it reads like a teammate instead like a spinner stuck on What's it doing: - Hover mid task and the state goes live: Writing code… Running tests… Reading docs… - Status sits on the icon, not buried three clicks deep Why it matters: - Trust in agents comes from knowing they're alive and working - Bake that into the nav and every screen you ship gets it for free

mateja

23,922 views • 2 months ago

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

57,554 views • 1 year ago

introducing Space: a cloud filesystem built for work instead of waiting, you can: → mount one persistent drive for you and your agents → instantly work in the cloud like local → only stream the bytes you need → no compression on any of your files try it for yourself today

introducing Space: a cloud filesystem built for work instead of waiting, you can: → mount one persistent drive for you and your agents → instantly work in the cloud like local → only stream the bytes you need → no compression on any of your files try it for yourself today

Jason Zhao

110,660 views • 12 days ago

the secret? there isn't one, it's just consistency. showing up on the days you don't feel like it is the whole game. no hacks, no shortcuts, just reps 😊 wearing @buffbunnycollection and you can use code miranda to save 10% off feeling like a hot girl in & out of the gym 😇 #consistency #fitnessmotivation #mindset #noshortcuts #grwm

the secret? there isn't one, it's just consistency. showing up on the days you don't feel like it is the whole game. no hacks, no shortcuts, just reps 😊 wearing @buffbunnycollection and you can use code miranda to save 10% off feeling like a hot girl in & out of the gym 😇 #consistency #fitnessmotivation #mindset #noshortcuts #grwm

Miranda Cohen

18,171 views • 2 months ago

Marketers. I’m begging you. Stop prompting Claude 12+ times when it can be done in 1. Most marketers open Claude and start typing whatever comes to mind. Several rounds later, you’re editing mediocre output by hand. My team built a prompt auditing tool that reads your work, grades it, and gets you to 95% in minutes. It’s based on the RCTC framework, which answers the 4 questions Claude actually needs to be effective: Role - WHO is this for? Channel - WHERE is this going? Task - WHAT outcome is the output getting to? Constraints - WHAT bad output sounds like? Then automatically edits your work so you’re more effective in Claude, ChatGPT, or Gemini. Comment “GA” and I’ll send you the tool.

Marketers. I’m begging you. Stop prompting Claude 12+ times when it can be done in 1. Most marketers open Claude and start typing whatever comes to mind. Several rounds later, you’re editing mediocre output by hand. My team built a prompt auditing tool that reads your work, grades it, and gets you to 95% in minutes. It’s based on the RCTC framework, which answers the 4 questions Claude actually needs to be effective: Role - WHO is this for? Channel - WHERE is this going? Task - WHAT outcome is the output getting to? Constraints - WHAT bad output sounds like? Then automatically edits your work so you’re more effective in Claude, ChatGPT, or Gemini. Comment “GA” and I’ll send you the tool.

Jesse Pujji

10,789 views • 4 months ago

AI video generation has come a long way. 🤯 You can now turn a simple prompt into a complete video — from scenes and characters to motion, camera angles, lighting, and visual effects. No complex editing. No hours of manual work. Just describe what you want, and AI can bring it to life. Want the exact prompt used to create videos like this? Comment “PROMPT” and I’ll share the free prompt link.

AI video generation has come a long way. 🤯 You can now turn a simple prompt into a complete video — from scenes and characters to motion, camera angles, lighting, and visual effects. No complex editing. No hours of manual work. Just describe what you want, and AI can bring it to life. Want the exact prompt used to create videos like this? Comment “PROMPT” and I’ll share the free prompt link.

Future Logic

11,131 views • 22 days ago

Claude Code + Nano Banana 2 is f*cking cracked 🤯 I built a skill inside Claude Code that writes JSON image prompts for Nano Banana 2, and the outputs look like they came from a professional photo shoot. One plain-text prompt. Claude rewrites it as structured JSON with lighting, camera, composition, style, and negative prompts. Then fires it off to Nano Banana 2. All inside Claude Code. Perfect for DTC brands and agencies who need high-volume ad creative without booking a shoot. If you're using Nano Banana 2 for product shots and lifestyle images but every generation feels like pulling a slot machine lever — random lighting, inconsistent style, plastic skin, misspelled labels ... This skill fixes the entire output: → You describe what you want in plain English → Claude rewrites it as a structured JSON prompt (lighting, camera angle, lens, depth of field, color grading — all of it) → Fires it to Nano Banana 2 via API → Saves the prompt + image in organized folders → You iterate on the style until it's dialed, then every output matches No more slot machine prompting. No more inconsistent brand imagery. No more burning credits on unusable generations. What you get: - Photo-realistic product shots and lifestyle images on demand - Full control over style, lighting, composition, and camera settings - Saved JSON prompts you can reuse across every campaign - A skill that gets smarter the more feedback you give it Built 100% in Claude Code with a custom skill + Python scripts. I put together a full playbook showing the exact skill, the JSON schema, and the workflow to set this up yourself. Want the full playbook? > Like this post > Comment "BANANA" And I'll send it over (must be following so I can DM)

NOVA

64,197 views • 6 months ago

Claude Code + Nano Banana 2 is f*cking cracked 🤯 I built a skill inside Claude Code that writes JSON image prompts for Nano Banana 2, and the outputs look like they came from a professional photo shoot. One plain-text prompt. Claude rewrites it as structured JSON with lighting, camera, composition, style, and negative prompts. Then fires it off to Nano Banana 2. All inside Claude Code. Perfect for DTC brands and agencies who need high-volume ad creative without booking a shoot. If you're using Nano Banana 2 for product shots and lifestyle images but every generation feels like pulling a slot machine lever — random lighting, inconsistent style, plastic skin, misspelled labels ... This skill fixes the entire output: → You describe what you want in plain English → Claude rewrites it as a structured JSON prompt (lighting, camera angle, lens, depth of field, color grading — all of it) → Fires it to Nano Banana 2 via API → Saves the prompt + image in organized folders → You iterate on the style until it's dialed, then every output matches No more slot machine prompting. No more inconsistent brand imagery. No more burning credits on unusable generations. What you get: - Photo-realistic product shots and lifestyle images on demand - Full control over style, lighting, composition, and camera settings - Saved JSON prompts you can reuse across every campaign - A skill that gets smarter the more feedback you give it Built 100% in Claude Code with a custom skill + Python scripts. I put together a full playbook showing the exact skill, the JSON schema, and the workflow to set this up yourself. Want the full playbook? > Like this post > Comment "BANANA" And I'll send it over (must be following so I can DM)

Mike Futia

212,649 views • 7 months ago