正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

SPEC IS BECOMING THE PRODUCT An Anthropic engineer gave Claude a spec, pointed it to an Asana board and left for the weekend. Claude broke it into tickets and spun up a team of agents. The agents started picking up tasks on their own. No one told them to.... show more

Shubham Saboo

118,413 subscribers

285,667 次观看 • 5 个月前 •via X (Twitter)

新闻政治教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

An engineer at Anthropic wrote a spec, pointed Claude at an Asana board, and went home. Claude broke the spec into tickets, spawned agents for each one, and they started building independently. When the agent is confused it runs git-blame and messages the right engineers in Slack. By Monday the agents finished the plugin feature. That's one example of how the best engineers are shipping software right now. Developers will soon orchestrate 50 AI agents in parallel and the difference between a good engineer & a great one would come down to specs. You can't write a spec that holds up at that scale without genuinely understanding what you're building at a deeper level. The next-gen developer who understands the fundamentals, can architect well and orchestrate agent is going to be a 1000x developer!

An engineer at Anthropic wrote a spec, pointed Claude at an Asana board, and went home. Claude broke the spec into tickets, spawned agents for each one, and they started building independently. When the agent is confused it runs git-blame and messages the right engineers in Slack. By Monday the agents finished the plugin feature. That's one example of how the best engineers are shipping software right now. Developers will soon orchestrate 50 AI agents in parallel and the difference between a good engineer & a great one would come down to specs. You can't write a spec that holds up at that scale without genuinely understanding what you're building at a deeper level. The next-gen developer who understands the fundamentals, can architect well and orchestrate agent is going to be a 1000x developer!

rvivek

1,242,662 次观看 • 5 个月前

Anthropic's Head of Claude Code: "I don't have a to-do list anymore. Claude just builds everything" he runs a tree of thousands of agents. agents prompting agents prompting agents one engineer set up a routine that auto-fixes any bug report not responded to in 5 hours. merges the easy ones himself Boris shipped a feature with an edge case. before he could fix it - another engineer's routine already had a PR up "Claude tells me this all the time. someone else has already fixed it. there's always another Claude working on it" 17 minutes. free. the most honest look at how the Claude Code team actually works bookmark & watch ↓

Anthropic's Head of Claude Code: "I don't have a to-do list anymore. Claude just builds everything" he runs a tree of thousands of agents. agents prompting agents prompting agents one engineer set up a routine that auto-fixes any bug report not responded to in 5 hours. merges the easy ones himself Boris shipped a feature with an edge case. before he could fix it - another engineer's routine already had a PR up "Claude tells me this all the time. someone else has already fixed it. there's always another Claude working on it" 17 minutes. free. the most honest look at how the Claude Code team actually works bookmark & watch ↓

Carnage

373,919 次观看 • 2 个月前

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

Anatoli Kopadze

311,157 次观看 • 2 个月前

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

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

Sprytix

65,797 次观看 • 8 天前

Anthropic Product Lead: "At Anthropic, our engineers are running swarms of 300+ agents daily. Give your agents 100+ tools - just don’t load them all into context." In a 30-minute talk, the Anthropic team shows how to deploy agents to production. Claude + loops + routines + dynamic workflows - that’s the secret. Watch the talk, then save the playbook below.

Anthropic Product Lead: "At Anthropic, our engineers are running swarms of 300+ agents daily. Give your agents 100+ tools - just don’t load them all into context." In a 30-minute talk, the Anthropic team shows how to deploy agents to production. Claude + loops + routines + dynamic workflows - that’s the secret. Watch the talk, then save the playbook below.

Movez

244,351 次观看 • 2 个月前

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper 📧

66,339 次观看 • 3 个月前

Built an open source MCP server for that allows Anthropic Claude to control the @PlayCanvas Editor. Just gave it the prompt "Build me a fun FPS level" and it just did it! This is a game-changer! 🤯

Built an open source MCP server for that allows Anthropic Claude to control the @PlayCanvas Editor. Just gave it the prompt "Build me a fun FPS level" and it just did it! This is a game-changer! 🤯

Will Eastcott

30,788 次观看 • 1 年前

ex-Anthropic engineer: "I left Anthropic to build agents systems in Google but nothing beats Claude as an agent yet - in coding and tool use, the rest are still behind " in this 90-min podcast, he showed how to build effective agent system with Claude from scratch to get into Anthropic, he hand-coded Karpathy's nanoGPT as a physicist Claude → tools → loops of verification → a real agent and why, at Google, he says Claude is the best watch & bookmark - then read the guide to agent systems ↓

ex-Anthropic engineer: "I left Anthropic to build agents systems in Google but nothing beats Claude as an agent yet - in coding and tool use, the rest are still behind " in this 90-min podcast, he showed how to build effective agent system with Claude from scratch to get into Anthropic, he hand-coded Karpathy's nanoGPT as a physicist Claude → tools → loops of verification → a real agent and why, at Google, he says Claude is the best watch & bookmark - then read the guide to agent systems ↓

codila

126,948 次观看 • 1 个月前

anthropic's head of product just revealed how they're able to ship faster than any other AI company. their secret: "side quest maxxing." here's how it works: instead of long-term roadmaps, anthropic runs on unplanned afternoon experiments. anyone on the team gets full freedom to spend an afternoon prototyping an idea and show it to the team. you get to skip the approval process entirely. then, employees at anthropic try it. if they keep using it the next day and the day after that, it gets polished into a real feature. if nobody touches it again, it dies. that's the whole process. claude code on desktop started as one engineer's afternoon project. he wanted it to work on desktop so he built a prototype. people on the team started using it immediately. so they shipped it. the todo list feature started the same way. someone built it, the team adopted it internally, and it became one of the most-used parts of the product. plugins started when one engineer shared a spec with claude code and the prototype that came back was close to production-ready. went from idea to working feature in a single session. they also killed standup meetings. instead of telling people what you're working on, you just show a working demo. all walk no talk basically the team structure makes this possible. > designers ship code. > engineers make product decisions. > product managers build prototypes. everyone can take an idea from concept to working demo without waiting on anyone else. the biggest features at a $380b company came from afternoon experiments that nobody asked for. honestly this matches my own experience cooking with ai. some of the best workflows i use every day came from just fucking around. opening a session with zero intention and asking claude what it can do, or jamming on a random idea to see where it goes. if you're only using ai for tasks you already have in mind, you're missing the best part. open a session with no agenda. ask it to surprise you. try building something stupid. half the time it goes nowhere. the other half it becomes the thing you use most. you need to be sidequestmaxxing.

anthropic's head of product just revealed how they're able to ship faster than any other AI company. their secret: "side quest maxxing." here's how it works: instead of long-term roadmaps, anthropic runs on unplanned afternoon experiments. anyone on the team gets full freedom to spend an afternoon prototyping an idea and show it to the team. you get to skip the approval process entirely. then, employees at anthropic try it. if they keep using it the next day and the day after that, it gets polished into a real feature. if nobody touches it again, it dies. that's the whole process. claude code on desktop started as one engineer's afternoon project. he wanted it to work on desktop so he built a prototype. people on the team started using it immediately. so they shipped it. the todo list feature started the same way. someone built it, the team adopted it internally, and it became one of the most-used parts of the product. plugins started when one engineer shared a spec with claude code and the prototype that came back was close to production-ready. went from idea to working feature in a single session. they also killed standup meetings. instead of telling people what you're working on, you just show a working demo. all walk no talk basically the team structure makes this possible. > designers ship code. > engineers make product decisions. > product managers build prototypes. everyone can take an idea from concept to working demo without waiting on anyone else. the biggest features at a $380b company came from afternoon experiments that nobody asked for. honestly this matches my own experience cooking with ai. some of the best workflows i use every day came from just fucking around. opening a session with zero intention and asking claude what it can do, or jamming on a random idea to see where it goes. if you're only using ai for tasks you already have in mind, you're missing the best part. open a session with no agenda. ask it to surprise you. try building something stupid. half the time it goes nowhere. the other half it becomes the thing you use most. you need to be sidequestmaxxing.

Ole Lehmann

106,072 次观看 • 3 个月前

🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use agents to help you spec, research, and decompose tasks Let your agents cook!

🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use agents to help you spec, research, and decompose tasks Let your agents cook!

Nicolae Rusan

16,654 次观看 • 1 年前

Anthropic just launched Computer-Use-Agents on Claude Desktop, meaning it can now take control of your entire computer environment. This is huge for businesses and enterprise, except it's limited by the fact that it requires a personal computer. If you deploy it into a virtual machine on Orgo, you can now manage hundreds or thousands of your clients' Claude accounts, setting up their skills, capabilities, connectors, etc, all on their own machines in the cloud on Orgo.

Anthropic just launched Computer-Use-Agents on Claude Desktop, meaning it can now take control of your entire computer environment. This is huge for businesses and enterprise, except it's limited by the fact that it requires a personal computer. If you deploy it into a virtual machine on Orgo, you can now manage hundreds or thousands of your clients' Claude accounts, setting up their skills, capabilities, connectors, etc, all on their own machines in the cloud on Orgo.

Nick Vasilescu

38,333 次观看 • 4 个月前

An AI engineer at Microsoft has just revealed how their teams build AI agents using Anthropic (Claude). It’s a free 34-minute workshop delivered directly by the Microsoft team. Save it to your favorites and watch it as soon as possible. 🔖 Opus 4.7 + more than 1,400 MCP tools already ready to use. You connect Claude to an agent → add tools → deploy it to production. It’s way more practical and useful than most of those “vibe-coding” courses that sell for 500).

An AI engineer at Microsoft has just revealed how their teams build AI agents using Anthropic (Claude). It’s a free 34-minute workshop delivered directly by the Microsoft team. Save it to your favorites and watch it as soon as possible. 🔖 Opus 4.7 + more than 1,400 MCP tools already ready to use. You connect Claude to an agent → add tools → deploy it to production. It’s way more practical and useful than most of those “vibe-coding” courses that sell for 500).

me

409,551 次观看 • 2 个月前

A 3-week-old store is pulling $7,000 week, and its owner barely touches it. No team. No agency. No copywriter. -> Investment: a $20 Claude subscription and one product photo. It runs on Ambaras. Hundreds of AI agents spun up 600+ versions of the store, A/B-tested them live, and pushed the winner to the front. Claude wrote every page, upsell and bundle, and generated the product images from that one photo. Sales pour in from everywhere at once: storefront, Instagram Shop, Tik Tok Shop, email. She opened the dashboard to check his numbers. 600 experiments had already picked the store that prints. Now she just watches it run. $7,000 a week. 3 weeks old. Do the math.

A 3-week-old store is pulling $7,000 week, and its owner barely touches it. No team. No agency. No copywriter. -> Investment: a $20 Claude subscription and one product photo. It runs on Ambaras. Hundreds of AI agents spun up 600+ versions of the store, A/B-tested them live, and pushed the winner to the front. Claude wrote every page, upsell and bundle, and generated the product images from that one photo. Sales pour in from everywhere at once: storefront, Instagram Shop, Tik Tok Shop, email. She opened the dashboard to check his numbers. 600 experiments had already picked the store that prints. Now she just watches it run. $7,000 a week. 3 weeks old. Do the math.

Ridark

13,387 次观看 • 1 个月前

The person who built Claude Code just explained how he is using it "Now I just have an army of agents that are doing stuff" Only 18 minutes, the best Claude guide on the internet right now. Boris Cherny covered: > how Claude Code is moving beyond just engineers > routines for CI, code review, and daily workflows > why the loop is the next big leap > working with hundreds of agents at once everything is already running through agents, ignoring this is not an option that's exactly why I wrote a full guide on how to build one yourself with Claude Code article below

The person who built Claude Code just explained how he is using it "Now I just have an army of agents that are doing stuff" Only 18 minutes, the best Claude guide on the internet right now. Boris Cherny covered: > how Claude Code is moving beyond just engineers > routines for CI, code review, and daily workflows > why the loop is the next big leap > working with hundreds of agents at once everything is already running through agents, ignoring this is not an option that's exactly why I wrote a full guide on how to build one yourself with Claude Code article below

Anatoli Kopadze

16,858 次观看 • 2 个月前

🚨 Agents can now book your flights, and pay for them. We just asked Claude (by Anthropic) to book us a ticket to JFK, and it did. Instantly. This works today, end-to-end with one simple integration.

🚨 Agents can now book your flights, and pay for them. We just asked Claude (by Anthropic) to book us a ticket to JFK, and it did. Instantly. This works today, end-to-end with one simple integration.

Crossmint

151,479 次观看 • 1 年前

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Notion

494,820 次观看 • 4 个月前

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any paid course on agents I've seen. Watch it, then read the guide on building loops below.

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any paid course on agents I've seen. Watch it, then read the guide on building loops below.

Anatoli Kopadze

2,128,282 次观看 • 27 天前

Superconductor: Manage an entire team of Claude Code agents, right from your phone or laptop. • Write informal tickets • Spin up MANY agents for each ticket • Each agent has its own live app preview • One-click PR the best one! Like this post and request early access👇

Superconductor: Manage an entire team of Claude Code agents, right from your phone or laptop. • Write informal tickets • Spin up MANY agents for each ticket • Each agent has its own live app preview • One-click PR the best one! Like this post and request early access👇

Sergey Karayev

34,926 次观看 • 1 年前

This Chinese developer runs 9 agents on Claude Code under a GPT-5.5 orchestrator and they close 500 client tasks a month without a single assistant. His client work is closed without him, on a single laptop and only three subscriptions. The entire system lives on one MacBook Pro M4 with 128 GB of memory and subscriptions to Claude Code and GPT-5.5 cost him approximately $300 a month. There is no CRM, no team, no office only a terminal window with 9 parallel streams. The orchestrator works with a simple system prompt: «You are the orchestrator of a client inbox. Classify every incoming email into 4 categories: code, content, analysis, communication. Delegate to the corresponding worker agent. When the result is ready, check it for completeness, send it to the client on my behalf, and mark the task as closed. Do not ask clarifying questions.» And the orchestrator checks the inbox every 30 seconds, classifies fresh emails, and distributes them to 9 worker agents on Claude Code, each of whom is responsible for their own class of tasks. Here is an example of how one of them closes a request to refactor a client's auth module: Task: refactor user-auth module Broke the monolith into 3 files by responsibilities Added unit tests, coverage increased to 87% Renamed 4 functions to camelCase according to the style guide PR is ready for review, link below» And so about 50 cycles a day. By noon 25 tasks are closed, by dinner 50, and by the end of the month 500. On average, it takes about 7 minutes from the appearance of an email in the inbox to sending the result to the client. This is more than what a live team of 6 developers, copywriters and analysts working 8 hours a day closes. This is no longer an agency. This is a workstation where an orchestrator replaces a manager, and 9 worker agents replace the staff. The pipeline goes from inbox to closing 500 times a month without human participation at any step.

This Chinese developer runs 9 agents on Claude Code under a GPT-5.5 orchestrator and they close 500 client tasks a month without a single assistant. His client work is closed without him, on a single laptop and only three subscriptions. The entire system lives on one MacBook Pro M4 with 128 GB of memory and subscriptions to Claude Code and GPT-5.5 cost him approximately $300 a month. There is no CRM, no team, no office only a terminal window with 9 parallel streams. The orchestrator works with a simple system prompt: «You are the orchestrator of a client inbox. Classify every incoming email into 4 categories: code, content, analysis, communication. Delegate to the corresponding worker agent. When the result is ready, check it for completeness, send it to the client on my behalf, and mark the task as closed. Do not ask clarifying questions.» And the orchestrator checks the inbox every 30 seconds, classifies fresh emails, and distributes them to 9 worker agents on Claude Code, each of whom is responsible for their own class of tasks. Here is an example of how one of them closes a request to refactor a client's auth module: Task: refactor user-auth module Broke the monolith into 3 files by responsibilities Added unit tests, coverage increased to 87% Renamed 4 functions to camelCase according to the style guide PR is ready for review, link below» And so about 50 cycles a day. By noon 25 tasks are closed, by dinner 50, and by the end of the month 500. On average, it takes about 7 minutes from the appearance of an email in the inbox to sending the result to the client. This is more than what a live team of 6 developers, copywriters and analysts working 8 hours a day closes. This is no longer an agency. This is a workstation where an orchestrator replaces a manager, and 9 worker agents replace the staff. The pipeline goes from inbox to closing 500 times a month without human participation at any step.

Blaze

29,917 次观看 • 3 个月前

introducing Ariana - the collaborative agentic IDE based on Claude Code - manage tasks with your team - give them to multiple coding agents with their own machine & branch - review with your team - agents merge for u comment "Better late than never" to get a build soon

introducing Ariana - the collaborative agentic IDE based on Claude Code - manage tasks with your team - give them to multiple coding agents with their own machine & branch - review with your team - agents merge for u comment "Better late than never" to get a build soon

Anicet

17,668 次观看 • 1 年前