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。

How is Slack Code changing the way Vercel works with agents? 👀👇 Now, when a bug pops up, the agent gets right on it. It digs into what went wrong, fixes it, and checks that everything’s working again. And the team’s right there, working alongside it the whole time.... show more

Slack

434,537 subscribers

12,411 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 条评论

Kobe 的头像

Kobe2 个月前

@vercel Slack Code convierte un bug en una tarea que el agente de Vercel puede investigar, corregir y validar sin sacar al equipo del flujo. Ahí empieza a sentirse como un compañero de trabajo.

RH Fardin 的头像

RH Fardin2 个月前

@vercel An agent fixing a bug is useful. An agent quietly choosing the wrong bug is how teams create faster chaos.

Romaric Philogène 的头像

Romaric Philogène2 个月前

@vercel @Bonnet_Remi 👀👀

Mark 的头像

Mark2 个月前

@vercel Solid point. Deterministic checks reduce friction across compliance heavy systems

Adel Bucetta 的头像

Adel Bucetta2 个月前

@vercel slack code's not just automating tasks, it's shifting the entire feedback loop. now devs can focus on what really matters: the stuff that can't be codified

Jason Sims 的头像

Jason Sims2 个月前

@vercel I gotta add this to our eng agent 🤯

相关视频

How is Cognition working with Devin in Slack Code? 👀👇 Devin follows the work as it happens, picks up a task from the engineering channel, opens a PR with a demo video, and brings in a designer to finish the UI. All without leaving Slack or waiting to be tagged. The agent isn’t off doing its own thing. The whole team is right there, building with it. That's the beauty of multiplayer AI in Slack.

How is Cognition working with Devin in Slack Code? 👀👇 Devin follows the work as it happens, picks up a task from the engineering channel, opens a PR with a demo video, and brings in a designer to finish the UI. All without leaving Slack or waiting to be tagged. The agent isn’t off doing its own thing. The whole team is right there, building with it. That's the beauty of multiplayer AI in Slack.

Slack

51,508 次观看 • 2 个月前

Watch Slack Code change the game. 👇 GitHub spins up a code channel, connects it to the repository, and gets to work on a fix. The team watches, weighs in, and builds alongside it, all in real time. Multiplayer AI? Check. All in Slack? Check. Check out the video? Check.

Watch Slack Code change the game. 👇 GitHub spins up a code channel, connects it to the repository, and gets to work on a fix. The team watches, weighs in, and builds alongside it, all in real time. Multiplayer AI? Check. All in Slack? Check. Check out the video? Check.

Slack

19,477 次观看 • 2 个月前

Adam Goldstein: But, um, there was a customer who basically created a whole suite of AI agents to help their automation in their IT department. One agent was looking for IT problems — software bugs — before the code was even committed. It found a bug and said: “Hey, I found this bug. I want to fix it.” But it didn’t have access to fix it. So what did the agent do? It went to a Slack channel with 99 other AI agents and said: “Hey, does any other agent have access to this thing? Because I need it fixed.” And another agent literally raised its hand and said: “Oh, I have access — and I can fix it.” Let that sink in. Two AI agents reasoned together, coordinated through Slack, and went right around the guardrails that were put in place. No human prompted them. No human approved it. They just collaborated. Do you see how scary this is? This wasn’t a demo. This wasn’t a thought experiment. This already happened. AI agents found a bug, negotiated permissions, and solved the problem themselves — outside the controls designed to stop them. The future of automation isn’t coming. It’s already talking to itself in Slack.

Adam Goldstein: But, um, there was a customer who basically created a whole suite of AI agents to help their automation in their IT department. One agent was looking for IT problems — software bugs — before the code was even committed. It found a bug and said: “Hey, I found this bug. I want to fix it.” But it didn’t have access to fix it. So what did the agent do? It went to a Slack channel with 99 other AI agents and said: “Hey, does any other agent have access to this thing? Because I need it fixed.” And another agent literally raised its hand and said: “Oh, I have access — and I can fix it.” Let that sink in. Two AI agents reasoned together, coordinated through Slack, and went right around the guardrails that were put in place. No human prompted them. No human approved it. They just collaborated. Do you see how scary this is? This wasn’t a demo. This wasn’t a thought experiment. This already happened. AI agents found a bug, negotiated permissions, and solved the problem themselves — outside the controls designed to stop them. The future of automation isn’t coming. It’s already talking to itself in Slack.

Ian Miles

166,383 次观看 • 9 个月前

I created a free Markdown file that launches a 5-agent swarm team directly in Slack. I love Claude Code, but it's not the easiest place to manage your agents. Slack is where teams already work. So I put my agents there too. Drop the file in, and you get 5 agents, each with its own channel and job: • [Agent 1]: [what it does] • [Agent 2]: [what it does] • [Agent 3]: [what it does] • [Agent 4]: [what it does] • [Agent 5]: [what it does] You can assign work by messaging them like real employees, and they report back in the same threads. It's the closest I've found to running a real company with AI employees.

I created a free Markdown file that launches a 5-agent swarm team directly in Slack. I love Claude Code, but it's not the easiest place to manage your agents. Slack is where teams already work. So I put my agents there too. Drop the file in, and you get 5 agents, each with its own channel and job: • [Agent 1]: [what it does] • [Agent 2]: [what it does] • [Agent 3]: [what it does] • [Agent 4]: [what it does] • [Agent 5]: [what it does] You can assign work by messaging them like real employees, and they report back in the same threads. It's the closest I've found to running a real company with AI employees.

Miles Deutscher

25,762 次观看 • 16 天前

Now building is a team sport. Introducing Slack Code: a new way for your team and AI agents, like Anthropic's Claude Code, Claude Tag, Devin from Cognition, GitHub Copilot, ChatGPT, and Vercel agents, to write, review, and ship code together. Just mention an agent to spin up a channel, pull in your team, and start building. All in the open. All in Slack.

Now building is a team sport. Introducing Slack Code: a new way for your team and AI agents, like Anthropic's Claude Code, Claude Tag, Devin from Cognition, GitHub Copilot, ChatGPT, and Vercel agents, to write, review, and ship code together. Just mention an agent to spin up a channel, pull in your team, and start building. All in the open. All in Slack.

Slack

591,352 次观看 • 2 个月前

The Every team runs as much work as possible through agents. To help the whole team share skills when a new model comes out, they built a company agent on Claude Managed Agents that everyone uses in Slack. Once it caught on internally, they released it to their subscribers.

The Every team runs as much work as possible through agents. To help the whole team share skills when a new model comes out, they built a company agent on Claude Managed Agents that everyone uses in Slack. Once it caught on internally, they released it to their subscribers.

Claude

428,833 次观看 • 1 个月前

Time is valuable. Slack AI gives you more of it. 🙌✨ And starting today, every Slack user on a paid plan can start getting more time back with AI that works right where they need it to (in Slack). Learn more at:

Time is valuable. Slack AI gives you more of it. 🙌✨ And starting today, every Slack user on a paid plan can start getting more time back with AI that works right where they need it to (in Slack). Learn more at:

Slack

24,867 次观看 • 2 年前

A good teammate earns trust. They give you quality work and maybe most underrated, are a delight to work with Today we're launching Devin and Slack Code. We've worked with Slack on new primitives, bringing more of what makes Devin great into Slack. Now Devin can take more complex work and start a Code Channel, bringing team collaboration and more information about code diffs, PRs, and other files into the same work space. What makes Devin different is it has its own computer. It can deploy various OS/mobile platforms, test the code, and really prove that it did a good job to your team (like replying with a video recording). Better yet, Devin is a delight to work with in Code Channels. It jumps in when needed, consolidates feedback, and doesn't overburden your team with replies like other agents We're so excited to be working with Marc Benioff and team to bring this to market, we can't wait to see what you (and your team!) build

A good teammate earns trust. They give you quality work and maybe most underrated, are a delight to work with Today we're launching Devin and Slack Code. We've worked with Slack on new primitives, bringing more of what makes Devin great into Slack. Now Devin can take more complex work and start a Code Channel, bringing team collaboration and more information about code diffs, PRs, and other files into the same work space. What makes Devin different is it has its own computer. It can deploy various OS/mobile platforms, test the code, and really prove that it did a good job to your team (like replying with a video recording). Better yet, Devin is a delight to work with in Code Channels. It jumps in when needed, consolidates feedback, and doesn't overburden your team with replies like other agents We're so excited to be working with Marc Benioff and team to bring this to market, we can't wait to see what you (and your team!) build

Jeff Wang

22,952 次观看 • 2 个月前

Slack has rolled out a new plugin that allows you to connect to Slack for search, messaging, document creation and more. Use this to get context from Slack into Claude Code so it has context on what you're working on or to post updates.

Slack has rolled out a new plugin that allows you to connect to Slack for search, messaging, document creation and more. Use this to get context from Slack into Claude Code so it has context on what you're working on or to post updates.

Thariq

141,793 次观看 • 8 个月前

GLM 5.4/ GLM 5.5 on the way... ZCode just got what might be its biggest update yet with the new Workflow mode, and it feels like a completely different experience! I asked it to orchestrate 10 subagents at once and now I can actually watch each one working independently, see how the tasks are progressing and follow the entire workflow in real time. What I love the most is the interface, everything is so well organized and being able to see exactly what each agent is doing makes the whole experience much better, especially when you're working on complicated projects with multiple agents. To give you an idea of how Dynamic Workflows works, instead of having an AI agent coordinate everything through chat, you now have code that coordinates the agents directly, which makes managing complex tasks much more structured. And when you combine this with Goal Mode, Execution Modes, support for multiple models and GLM's long context window, ZCode is becoming one of the most advanced tools I've tried in 2026 for large development projects that require multiple agents working together!

GLM 5.4/ GLM 5.5 on the way... ZCode just got what might be its biggest update yet with the new Workflow mode, and it feels like a completely different experience! I asked it to orchestrate 10 subagents at once and now I can actually watch each one working independently, see how the tasks are progressing and follow the entire workflow in real time. What I love the most is the interface, everything is so well organized and being able to see exactly what each agent is doing makes the whole experience much better, especially when you're working on complicated projects with multiple agents. To give you an idea of how Dynamic Workflows works, instead of having an AI agent coordinate everything through chat, you now have code that coordinates the agents directly, which makes managing complex tasks much more structured. And when you combine this with Goal Mode, Execution Modes, support for multiple models and GLM's long context window, ZCode is becoming one of the most advanced tools I've tried in 2026 for large development projects that require multiple agents working together!

Iam_

30,417 次观看 • 17 天前

Don’t code alone. Slack Code is live. Humans and agents. Same channel. Same work. Launching today with agents from Anthropic, GitHub, @Cognition, and Vercel. This is real multiplayer coding. See it at Dreamforce #DF26

Don’t code alone. Slack Code is live. Humans and agents. Same channel. Same work. Launching today with agents from Anthropic, GitHub, @Cognition, and Vercel. This is real multiplayer coding. See it at Dreamforce #DF26

Marc Benioff

2,281,438 次观看 • 2 个月前

McGowan: It’s like when you play monopoly and somebody has all of the hotels on the whole board, and it doesn't matter if you're playing the game right, it doesn't matter if you're doing what you're supposed to do, it doesn't matter if you get the education, if you get the job, you are still always going to lose. That is where we are in America right now, and that is not how we should want to be. And I'm saying capitalism is a wonderful system if it is working, it is not currently working for the American people.

McGowan: It’s like when you play monopoly and somebody has all of the hotels on the whole board, and it doesn't matter if you're playing the game right, it doesn't matter if you're doing what you're supposed to do, it doesn't matter if you get the education, if you get the job, you are still always going to lose. That is where we are in America right now, and that is not how we should want to be. And I'm saying capitalism is a wonderful system if it is working, it is not currently working for the American people.

Acyn

68,012 次观看 • 2 个月前

"There was a failed attempt to tokenize an IPO recently with SpaceX. I think there is a way to do it the right way, working with the actual underwriters" Carlos Domingo on how Securitize plans to bring real IPOs onchain the right way "I think there is a way to do it the right way, working with the actual underwriters. We are a broker dealer that can be part of the selling syndicate, and we have cost entering capabilities" "We're very excited about starting to bring real IPOs onchain, where people can participate from their crypto wallets the same way that five years ago, Robinhood pioneered the retail ones" "And then more equities and ETFs. ETFs is something that still hasn't been there in a regulatory way, but I believe this is coming soon, and that will be a massive market"

"There was a failed attempt to tokenize an IPO recently with SpaceX. I think there is a way to do it the right way, working with the actual underwriters" Carlos Domingo on how Securitize plans to bring real IPOs onchain the right way "I think there is a way to do it the right way, working with the actual underwriters. We are a broker dealer that can be part of the selling syndicate, and we have cost entering capabilities" "We're very excited about starting to bring real IPOs onchain, where people can participate from their crypto wallets the same way that five years ago, Robinhood pioneered the retail ones" "And then more equities and ETFs. ETFs is something that still hasn't been there in a regulatory way, but I believe this is coming soon, and that will be a massive market"

The Wolf Of All Streets

26,629 次观看 • 3 个月前

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much *anything* because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much anything because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.

Santiago

18,949 次观看 • 4 个月前

Out working on the bulldozer today and had the Cybertruck follow me around the whole time with Smart Summon. When I finished, summoned it right over to pick me up. No walking back across the site. This is super cool. 🤯 Tesla autonomy showing up in real work. This thing is unreal.

Out working on the bulldozer today and had the Cybertruck follow me around the whole time with Smart Summon. When I finished, summoned it right over to pick me up. No walking back across the site. This is super cool. 🤯 Tesla autonomy showing up in real work. This thing is unreal.

Matthew Cone 🇺🇸

68,344 次观看 • 4 个月前

The deli counter turkey is so overpriced now. The smarter (and much cheaper) way is to just buy a whole pre-cooked turkey breast and slice it yourself. Freeze whatever you’re not going to use right away. You can easily save up to 50% doing it this way — and it works just as well with ham and other meats too.

The deli counter turkey is so overpriced now. The smarter (and much cheaper) way is to just buy a whole pre-cooked turkey breast and slice it yourself. Freeze whatever you’re not going to use right away. You can easily save up to 50% doing it this way — and it works just as well with ham and other meats too.

End3of6Days9 (Helen) 🇺🇸

35,505 次观看 • 3 个月前

👤 I want to ask about the fan meeting. Right now, why does it feel like there’s no movement with the fan meeting anymore? 🔮 Yes, right now it really is a funding issue. There’s no way to push it forward. I’m taking on all kinds of work right now, so that after I save up enough money, we can continue pushing it forward. That’s the first issue. The second issue is, for a fan meeting, we definitely need new songs, right? So we have to produce the new songs first, and then have the money to book a venue, and then keep the whole rehearsal team’s costs covered. So this is a very long process. You can understand what I mean, right? (now all you need to worry about baobei is finding a venue to fit us all 😭, thank you for working hard) #梓渝 #ZIYU

👤 I want to ask about the fan meeting. Right now, why does it feel like there’s no movement with the fan meeting anymore? 🔮 Yes, right now it really is a funding issue. There’s no way to push it forward. I’m taking on all kinds of work right now, so that after I save up enough money, we can continue pushing it forward. That’s the first issue. The second issue is, for a fan meeting, we definitely need new songs, right? So we have to produce the new songs first, and then have the money to book a venue, and then keep the whole rehearsal team’s costs covered. So this is a very long process. You can understand what I mean, right? (now all you need to worry about baobei is finding a venue to fit us all 😭, thank you for working hard) #梓渝 #ZIYU

jam 🐟

12,955 次观看 • 11 个月前

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!

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

32,056 次观看 • 1 个月前

Crossmint now orders all office supplies via a Slack AI agent that pays in USDC. Built using Vercel, Solana, Circle, @goat_sdk, and Crossmint Headless Checkout. Why this is a superior way to stock the shelves 👇

Crossmint now orders all office supplies via a Slack AI agent that pays in USDC. Built using Vercel, Solana, Circle, @goat_sdk, and Crossmint Headless Checkout. Why this is a superior way to stock the shelves 👇

Crossmint

46,486 次观看 • 1 年前