Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not...

undefinedKi's profile picture

Yarchi

17,039 subscribers

462,665 görüntüleme • 3 ay önce •via X (Twitter)

EğitimHaberler & PolitikaBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

38 Yorum

Nahid profil fotoğrafı
Nahid3 ay önce

3-4x the tokens is a lot to commit to

Yarchi profil fotoğrafı
Yarchi3 ay önce

yes, worth installing

Michael profil fotoğrafı
Michael3 ay önce

Agent Teams has been a thing since Opus 4.7 was released. 🙃 FYI, best used with tmux.

Vanta Omega profil fotoğrafı
Vanta Omega3 ay önce

people just be writing bullshit these days. agent teams has been out for a while, its not "JUST QUIETLY SHIPPED"

rewind profil fotoğrafı
rewind3 ay önce

agent teams are the real unlock

Yarchi profil fotoğrafı
Yarchi3 ay önce

totally agree

Charlie profil fotoğrafı
Charlie3 ay önce

This isn’t something new, it has been for a while since February

starmex profil fotoğrafı
starmex3 ay önce

bookmarked, thanks for the alpha!

Yarchi profil fotoğrafı
Yarchi3 ay önce

glad it worked

rari profil fotoğrafı
rari3 ay önce

agent teams feel perfect for work that can actually split in parallel

Yarchi profil fotoğrafı
Yarchi3 ay önce

100%

AI Image Pro profil fotoğrafı
AI Image Pro3 ay önce

Agent teams has been out for some time tbh you needed to set it in settings.json However 4 to 7 times the tokens is a high price.

Chris profil fotoğrafı
Chris3 ay önce

is anyone actually shipping prod with this or are we just watching agents have meetings with each other for 4x the tokens??

Gipp 🦅 profil fotoğrafı
Gipp 🦅3 ay önce

the launch is very simple

Yarchi profil fotoğrafı
Yarchi3 ay önce

yeah, anyone will figure out

Nekt0 profil fotoğrafı
Nekt03 ay önce

Very good

BIG AL profil fotoğrafı
BIG AL3 ay önce

Been using this for awhile lol Tip make a c level board of directors

jingo profil fotoğrafı
jingo3 ay önce

the task-list sharing is the part that actually matters. spawning agents is easy, keeping them from clobbering each other isn't. worktree isolation per agent is what makes parallel edits not stomp the same files.

pre.dev profil fotoğrafı
pre.dev3 ay önce

Agent teams are a real step up, but parallel agents without a shared plan just produce parallel mess faster. The team lead is only as good as the architecture and task graph it's coordinating around. The planning layer is what turns spawned agents into an actual team.

Ridark profil fotoğrafı
Ridark3 ay önce

Came back a week later, found new layers I missed

bodila profil fotoğrafı
bodila3 ay önce

wooow, first time see it thx bro, will try

SSOT profil fotoğrafı
SSOT3 ay önce

Shipped? This is in for like a year now way before workflows etc.

Insomnia profil fotoğrafı
Insomnia3 ay önce

I think in future it will be better else

Neuromancer profil fotoğrafı
Neuromancer3 ay önce

@thsottiaux when in Codex ?

Argona profil fotoğrafı
Argona3 ay önce

nice vid, will read your article also soon, a really exciting feature

henricgn profil fotoğrafı
henricgn3 ay önce

This has been out for months man

Renzo profil fotoğrafı
Renzo3 ay önce

Been doing this for a while. If you want to check it iut, is open source and self hosted optional. AGPL.

Joe Smith profil fotoğrafı
Joe Smith3 ay önce

Want a quick way to spend loads of cash. You have found it! I can’t help but think these people are getting paid by Anthropic?

MostAgile | TechLead187 profil fotoğrafı
MostAgile | TechLead1873 ay önce

Highly inefficient for anything except rapid prototyping or full Dev team replacement. If you’re growing rapidly, solo-pioneer, or Scrooge McDuck replacing humans with tokens/silicon this makes sense.

YaMi(reply/shitpost arc) profil fotoğrafı
YaMi(reply/shitpost arc)3 ay önce

sounds like a really cool feature, but is it really sustainable with x3-4 tokens spend, on top of the fact that claude is the most expensive LLM API already? Still pretty useful for people with budget and tight deadlines

海印AI编程 profil fotoğrafı
海印AI编程3 ay önce

I literally do this manually with 3 terminal windows. if this is native now I'm both excited and unemployedI literally do this manually with 3 terminal windows. if this is native now I'm both excited and unemployed

Cody profil fotoğrafı
Cody3 ay önce

and it only uses 10x more tokens and takes 20x as long!!!!!! But hey at least you could use Fable..... oh wait

rvaniaaa profil fotoğrafı
rvaniaaa3 ay önce

What’s fascinating is that the org chart survived. We just replaced some of the people with agents.

Etienne Cowley profil fotoğrafı
Etienne Cowley3 ay önce

This have been around for a long time...not released recently.

Nick H profil fotoğrafı
Nick H3 ay önce

The agent teams feature has been there for half a year already

Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API profil fotoğrafı
Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API3 ay önce

这个我也刚看到，确实挺突然的。说实话 agent team 这个方向很有意思，但我现在更关心它会不会乱开会、狂烧 token。能把互审做稳，比单纯多几个 agent 更有用。

Peter Skøtt Pedersen profil fotoğrafı
Peter Skøtt Pedersen3 ay önce

This is over a year old

Timur Yessenov profil fotoğrafı
Timur Yessenov3 ay önce

I’d only turn this on when the work has real seams: frontend, backend, QA, docs. If 3 agents touch the same file, the token bill becomes a coordination tax. The win is separate contexts plus one boring merge note at the end.

Benzer Videolar

Claude Code now has Agent Teams Multiple Claude sessions working in parallel, coordinating through shared tasks and messaging each other. Enable it by adding this to your settings.json: { "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS":"1" } } Just describe the team you want in plain English Shift+↑ to check each teammate's progress This + worktrees = workflow multiplier
0:27

Claude Code now has Agent Teams Multiple Claude sessions working in parallel, coordinating through shared tasks and messaging each other. Enable it by adding this to your settings.json: { "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS":"1" } } Just describe the team you want in plain English Shift+↑ to check each teammate's progress This + worktrees = workflow multiplier

Daniel San

83,388 görüntüleme • 7 ay önce

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.
55:30

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

32,199 görüntüleme • 2 ay önce

Claude Code now supports agent teams (in research preview) Instead of a single agent working through a task sequentially, a lead agent can delegate to multiple teammates that work in parallel to research, debug, and build while coordinating with each other. Try it out today by enabling agent teams in your settings.json!
0:40

Claude Code now supports agent teams (in research preview) Instead of a single agent working through a task sequentially, a lead agent can delegate to multiple teammates that work in parallel to research, debug, and build while coordinating with each other. Try it out today by enabling agent teams in your settings.json!

Lydia Hallie ✨

1,445,338 görüntüleme • 7 ay önce

I managed to unlock a crazy new hidden feature in Claude Code called Swarms. You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes. When you approve a plan, it enters a new "delegation mode" and spawns a team of specialists who: - Share a task board with dependencies - Work in parallel as teammates - Message each other to coordinate work Workers do the heavy lifting, coordinate amongst themselves, then report back.
3:35

I managed to unlock a crazy new hidden feature in Claude Code called Swarms. You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes. When you approve a plan, it enters a new "delegation mode" and spawns a team of specialists who: - Share a task board with dependencies - Work in parallel as teammates - Message each other to coordinate work Workers do the heavy lifting, coordinate amongst themselves, then report back.

Mike Kelly

566,637 görüntüleme • 8 ay önce

Anthropic senior engineer just revealed how to use Claude Code at 110% in a 47-minute session. 47-minutes. free. by Anthropic team. worth more than any $500 vibe-coding course here's what she covers: • 3 things Claude needs: access, knowledge, tooling • git worktrees + one Claude each = a team you manage • /loop that babysits PRs and fixes CI overnight • agents that message each other while you sleep most people use Claude on one repo in one window - while the people who get this run teams of agents in parallel watch the full talk, then read the article below
46:58

Anthropic senior engineer just revealed how to use Claude Code at 110% in a 47-minute session. 47-minutes. free. by Anthropic team. worth more than any $500 vibe-coding course here's what she covers: • 3 things Claude needs: access, knowledge, tooling • git worktrees + one Claude each = a team you manage • /loop that babysits PRs and fixes CI overnight • agents that message each other while you sleep most people use Claude on one repo in one window - while the people who get this run teams of agents in parallel watch the full talk, then read the article below

Codez

71,312 görüntüleme • 3 ay önce

Had Claude Code build a little plugin that visualizes the work Claude Code is doing as agents working in an office, with agents doing work and passing information to each other. New subagents are hired, they acquire skills, and they turn in completed work. Fun start.
0:48

Had Claude Code build a little plugin that visualizes the work Claude Code is doing as agents working in an office, with agents doing work and passing information to each other. New subagents are hired, they acquire skills, and they turn in completed work. Fun start.

Ethan Mollick

468,554 görüntüleme • 8 ay önce

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this
0:24

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

58,591 görüntüleme • 3 ay önce

Quick demo of how I use session to session messaging in Claude Code + Ghostty (Save this and try it in your own workflows) 1- I always start with a regular session and a panel running claude agents 2- The first session becomes the orchestrator. It creates the initial context, then distributes the work across other sessions using forks 3- Each fork starts with that context + a prompt telling it what to work on 4- I rename each session with ctrl + r to keep things organized and make it easy to message them from the main session 5- Using @ I send messages to the sessions that are running and ask them to report their task status back, so the main session always knows what everyone is working on This way, I only need 2 or 3 panels open and can switch between tasks as needed The days of opening endless terminal panels and running Claude Code 100 times just to look productive are over! What we need now is ORCHESTATION one main session coordinating everything through session messaging + Agent View And the key is context, build it in the main session first, then fork from there That’s what makes the entire workflow click
0:28

Quick demo of how I use session to session messaging in Claude Code + Ghostty (Save this and try it in your own workflows) 1- I always start with a regular session and a panel running claude agents 2- The first session becomes the orchestrator. It creates the initial context, then distributes the work across other sessions using forks 3- Each fork starts with that context + a prompt telling it what to work on 4- I rename each session with ctrl + r to keep things organized and make it easy to message them from the main session 5- Using @ I send messages to the sessions that are running and ask them to report their task status back, so the main session always knows what everyone is working on This way, I only need 2 or 3 panels open and can switch between tasks as needed The days of opening endless terminal panels and running Claude Code 100 times just to look productive are over! What we need now is ORCHESTATION one main session coordinating everything through session messaging + Agent View And the key is context, build it in the main session first, then fork from there That’s what makes the entire workflow click

Daniel San

63,319 görüntüleme • 1 ay önce

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇
29:58

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

darkzodchi

845,668 görüntüleme • 4 ay önce

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:
2:58

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:

Warp

20,810 görüntüleme • 4 ay önce

this guy built an app where AI agents autonomously create tasks, review each other's work, and message each other you just sit there and watch everything happen on a dashboard in real time agents: > assign work to other agents > review the output > send messages back and forth. > flag issues and iterate. you're basically watching a team operate without you. there are endless opportunities to automate your life with this AND its free + open source.
4:22

this guy built an app where AI agents autonomously create tasks, review each other's work, and message each other you just sit there and watch everything happen on a dashboard in real time agents: > assign work to other agents > review the output > send messages back and forth. > flag issues and iterate. you're basically watching a team operate without you. there are endless opportunities to automate your life with this AND its free + open source.

Om Patel

28,547 görüntüleme • 6 ay önce

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.
3:10

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

The Startup Ideas Podcast (SIP) 🧃

18,006 görüntüleme • 1 ay önce

THIS GUY MADE CLAUDE CODE AND CODEX TALK TO EACH OTHER not by switching between them, they literally talk to each other about your code in real time you give it a task. it spawns a Claude agent and a Codex agent in separate sessions. they share findings, challenge each other, and produce a combined result. he pointed them at an Express API with intentional security issues. within minutes they found SQL injection, hardcoded secrets, missing auth, and weak JWT config. one catches something and the other confirms it and adds context. they divide the work on their own for faster speed one command: /collab "review auth.js for security issues" that's it. you watch the conversation happen in real time. AND its open source with new models being integrated crazy to think that this was entirely vibe coded
1:09

THIS GUY MADE CLAUDE CODE AND CODEX TALK TO EACH OTHER not by switching between them, they literally talk to each other about your code in real time you give it a task. it spawns a Claude agent and a Codex agent in separate sessions. they share findings, challenge each other, and produce a combined result. he pointed them at an Express API with intentional security issues. within minutes they found SQL injection, hardcoded secrets, missing auth, and weak JWT config. one catches something and the other confirms it and adds context. they divide the work on their own for faster speed one command: /collab "review auth.js for security issues" that's it. you watch the conversation happen in real time. AND its open source with new models being integrated crazy to think that this was entirely vibe coded

Om Patel

25,318 görüntüleme • 6 ay önce

As soon as you try to run 2 agents on the same data, everything breaks: • Agent 1 reads some data and starts working. • Two seconds later, Agent 2 changes that same data. This is a problem. Agents will waste tokens on stale data, overwrite each other's work, and redo tasks the other has already finished. You can't prompt your way out of this mess. Everything old in software engineering is new again. We need proper coordination when running multiple agents. Here is a good open-source solution for this: Omnigraph is a graph database for context assembly and multi-agent coordination. Here is how it works: • It sets one shared place where multiple agents will work from • Each agent gets their own copy of the data • Agents write their changes to their copy • When an agent is done, it merges its changes back Three huge benefits from this model: 1. We know it works. We've been doing this for decades already. 2. No more lost information or agents stepping on each other's toes. 3. You get a complete trail of which agent did what and when. I recorded a video to show you a bit more about this. Here is the link to the Omnigraph GitHub repository:
6:51

As soon as you try to run 2 agents on the same data, everything breaks: • Agent 1 reads some data and starts working. • Two seconds later, Agent 2 changes that same data. This is a problem. Agents will waste tokens on stale data, overwrite each other's work, and redo tasks the other has already finished. You can't prompt your way out of this mess. Everything old in software engineering is new again. We need proper coordination when running multiple agents. Here is a good open-source solution for this: Omnigraph is a graph database for context assembly and multi-agent coordination. Here is how it works: • It sets one shared place where multiple agents will work from • Each agent gets their own copy of the data • Agents write their changes to their copy • When an agent is done, it merges its changes back Three huge benefits from this model: 1. We know it works. We've been doing this for decades already. 2. No more lost information or agents stepping on each other's toes. 3. You get a complete trail of which agent did what and when. I recorded a video to show you a bit more about this. Here is the link to the Omnigraph GitHub repository:

Santiago

27,851 görüntüleme • 4 gün önce

What's the actual setup work behind running a team of AI agents on Buzz? Almost none. The one move that mattered: pin each agent to a model. "Fizz is a Fable model and Honey is Sonnet" Certain tasks don't need Fable's power, and running them there burns through tokens fast. Then I made a chief agent officer — an agent whose only job is deciding which agent gets the task. Copywriter, brainstormer, code reviewer. You forget who they all are. It doesn't. Claude Code is the harness underneath, and every skill you've already got installed globally comes with it. The catch: this is early preview software, maybe alpha. Recurring tasks and workflows "weren't really landing great," and the relay round-trip to the server makes it slower than sitting in Claude Code directly. Solopreneurs and small teams iterating on small ideas, this is a great tool. Complex software engineering, not yet. Just start playing around.
3:24

What's the actual setup work behind running a team of AI agents on Buzz? Almost none. The one move that mattered: pin each agent to a model. "Fizz is a Fable model and Honey is Sonnet" Certain tasks don't need Fable's power, and running them there burns through tokens fast. Then I made a chief agent officer — an agent whose only job is deciding which agent gets the task. Copywriter, brainstormer, code reviewer. You forget who they all are. It doesn't. Claude Code is the harness underneath, and every skill you've already got installed globally comes with it. The catch: this is early preview software, maybe alpha. Recurring tasks and workflows "weren't really landing great," and the relay round-trip to the server makes it slower than sitting in Claude Code directly. Solopreneurs and small teams iterating on small ideas, this is a great tool. Complex software engineering, not yet. Just start playing around.

The Startup Ideas Podcast (SIP) 🧃

24,769 görüntüleme • 1 ay önce

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep. [The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents] ↓ Save this before everyone copies the playbook 1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine 2. Validation contract before code, not after. Humans only at scoping and review. 3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role. Watch the guide. Then read the guide below by Khairallah AL-Awady
9:37

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep. [The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents] ↓ Save this before everyone copies the playbook 1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine 2. Validation contract before code, not after. Humans only at scoping and review. 3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role. Watch the guide. Then read the guide below by Khairallah AL-Awady

Avid

638,269 görüntüleme • 4 ay önce

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!
31:29

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

GREG ISENBERG

30,787 görüntüleme • 11 gün önce

We made Agent Design real before Claude Design became part of Claude Code. Open Design brings a live, editable artboard to any agent. Find it in the Codex Plugin Directory, or use the prompt below for Claude and other AI agents. ↘️
0:21

We made Agent Design real before Claude Design became part of Claude Code. Open Design brings a live, editable artboard to any agent. Find it in the Codex Plugin Directory, or use the prompt below for Claude and other AI agents. ↘️

OpenDesign

42,759 görüntüleme • 1 ay önce

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call
1:07

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call

Shadow Nick

14,714 görüntüleme • 3 ay önce

I tested how a team of four agents could work together to build something For this example, I had 4 agents take on the roles of product manager, designer, QA, and engineer It was surprisingly fun to watch them work through the problem together and challenge each other along the way. I found the QA agent especially useful, since that extra pass at the end caught a lot of small UI bugs. Bloome
0:36

I tested how a team of four agents could work together to build something For this example, I had 4 agents take on the roles of product manager, designer, QA, and engineer It was surprisingly fun to watch them work through the problem together and challenge each other along the way. I found the QA agent especially useful, since that extra pass at the end caught a lot of small UI bugs. Bloome

Ian Zelbo

51,339 görüntüleme • 2 ay önce