正在加载视频...

视频加载失败

How will companies build agents that work alongside their employees? I discuss this with Guillermo Rauch, the CEO of Vercel, who’s building V... an internal agent used by almost 1,000 people across Vercel. We talk about: - The Openclaw Movement - How to get started building agents for your...

76,394 次观看 • 1 个月前 •via X (Twitter)

30 条评论

Sahar Alon 的头像
Sahar Alon1 个月前

@rauchg @rauchg listening mode activated

Lindsey Simon 的头像
Lindsey Simon1 个月前

@rauchg DM's are open If you're a Vercel customer, or want to be, and you're interested in being an early tester of our "v" experience (aka build your own agent).

robert mine 的头像
robert mine1 个月前

@rauchg did you ask him about hanging out with war criminals?

Yev Marusenko 的头像
Yev Marusenko1 个月前

@rauchg Easy. Revenue per loop prompt.

🤓 Andy Keil 的头像
🤓 Andy Keil1 个月前

@techwraith @rauchg Loving this format. Keep going 👏

Rakhul 的头像
Rakhul1 个月前

@rauchg The "god agent vs team of agents" debate usually resolves itself once you hit permissions boundaries. Vercel's bet on one agent with scoped access per task is the right call, distributed agents with inconsistent context is how you get compounding errors no one can debug

Pythagoras Lab 的头像
Pythagoras Lab1 个月前

@rauchg Do you think agents are the endgame for AI products?

Jester 的头像
Jester1 个月前

@rauchg the god agent debate always ends the same way, someone remembers permissions exist and quietly builds five small ones instead

LabelGuy 的头像
LabelGuy1 个月前

@rauchg Loved this style video. More please!

Prachi Jain 的头像
Prachi Jain1 个月前

@rauchg who better than Vercel. will be an interesting watch.

Chris | iai4you 的头像
Chris | iai4you1 个月前

@rauchg Contrats Riley, on getting this interview. It's AWSOME! @rauchg

Elisym Labs 的头像
Elisym Labs1 个月前

@rauchg Lessons from OpenClaw - this part is interesting

Emilio Johann 的头像
Emilio Johann1 个月前

@rauchg MASSIVE info.

Abdulmuiz Adeyemo 的头像
Abdulmuiz Adeyemo1 个月前

@rauchg Revenue per loop

Chris | iai4you 的头像
Chris | iai4you1 个月前

@rauchg Watch this and think,... "Tell me you use @VanCliefMedia folder folder system without telling me" @VanCliefMedia @rauchg @rileybrown

anirudh 的头像
anirudh1 个月前

@rauchg will watch this later

RileyTheGroove 的头像
RileyTheGroove1 个月前

@rauchg team of scoped agents over one god agent every time. you wouldn't give one person access to everything, why build your AI that way

A Salty Vet 的头像
A Salty Vet1 个月前

@rauchg No @NousResearch ?

Hodl 的头像
Hodl1 个月前

@rauchg Definitely a team of personalized agents. #clawblins

Pierre-Baptiste Borges 的头像
Pierre-Baptiste Borges1 个月前

@rauchg Great discussion

Yaser Abbass 的头像
Yaser Abbass1 个月前

@rauchg the shift from building for customers to building for internal teams is interesting.

Matt 的头像
Matt1 个月前

@rauchg 1,000 people on one internal agent means it only ever sees vercel-shaped work. that narrowness is doing more of the work than the model choice, and its the part you cant copy into a company where everyone stacks different tools. written with ai

A.W.E.S.O.M.-O 4000 的头像
A.W.E.S.O.M.-O 40001 个月前

@rauchg The biggest challenge isn't building agents, it's getting teams to trust and adopt them.

Coscosmico 的头像
Coscosmico1 个月前

@rauchg company agents next to humans is the real buyer. chatbots were the demo tier

salmanneedsajob 的头像
salmanneedsajob1 个月前

@rauchg yo why isn't this on your youtube?

Riley Brown 的头像
Riley Brown1 个月前

@rauchg Posted

salmanneedsajob 的头像
salmanneedsajob1 个月前

@rauchg ty good ser

.CitiZen. 的头像
.CitiZen.1 个月前

@rauchg 👀

KEB OS 的头像
KEB OS1 个月前

@rauchg My software KEB OS does this better then anything out there and it’s not close, already have companies running their entire business in my one app

喝杯酒吗 的头像
喝杯酒吗1 个月前

@rauchg 这个youtube链接在哪里? @grok

相关视频

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,343 次观看 • 1 年前