Loading video...

Video Failed to Load

Go Home

The Vercel fluid × Upstash agents framework just solved one of the trickiest issues in chatbots/agents and one of my biggest pet peeves 😆 Notice that right after submitting my message, it immediately assigns an uuid (`/wfr_KgW5x…`) to the job. At this point, my internet might flake out, I...

56,799 views • 1 year ago •via X (Twitter)

11 Comments

Guillermo Rauch's profile picture
Guillermo Rauch1 year ago

Example of @wolfram_alpha being chosen by the agent: "give me 50 digits of pi"

MightyBot's profile picture
MightyBot1 year ago

🧠 Unified Search. Smarter Meetings. Effortless CRM. MightyBot is your AI agent platform for seamless workflows—record meetings, automate CRM updates, and find answers across apps in seconds. 🌟 Focus on what matters. We'll handle the grind.

Dan ⚡️'s profile picture
Dan ⚡️1 year ago

@vercel @upstash went to my gf and screamed: "babe, Guillermo just made a resumable, durable agentic workflow that's fault tolerant on the server AND on the client" sleeping on the couch again tonight

yunus's profile picture
yunus1 year ago

@vercel @upstash It was a pleasure collaborating on this, persisting the session took the application to another level.

Batsirai's profile picture
Batsirai1 year ago

@upstash @vercel Can one agent handle requests from a multitenant environment with many users making the same request, but with responses allocated to specific users?

Guillermo Rauch's profile picture
Guillermo Rauch1 year ago

@upstash @vercel Yes

Jack's profile picture
Jack1 year ago

@vercel @upstash What would it take to be able to hook into the stream during these tasks? would be sick to be able to, on refresh, 1. get latest values 2. see updates stream in

Guillermo Rauch's profile picture
Guillermo Rauch1 year ago

@vercel @upstash Should be doable with Redis streams? We’ll take a look

Samo 🇪🇺 eu/acc's profile picture
Samo 🇪🇺 eu/acc1 year ago

@vercel @upstash this is very easy doable also using ActorCore from Rivet and can be selfhosted / hosted on different providers :)) It’s top notch DX

Brennan McEachran 👨‍🚀's profile picture
Brennan McEachran 👨‍🚀1 year ago

@vercel @upstash Been using @samejr’s for this and it’s been phenomenal. The saddest part is that I’m using next way less

Yunus Emre Ozer's profile picture
Yunus Emre Ozer1 year ago

@vercel @upstash Damn I thought you mentioned me for a sec 😂

Related Videos

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."

TBPN

35,595 views • 3 months ago

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 views • 1 year ago

OMG, Listen To This 🚨 Kristen Meghan worked for the U.S. Air Force as an environmental specialist She set out to debunk Chemtrails “In the process of trying to debunk it, I realized it was actually coming right out of my office I was one of the people approving the chemicals” “Military veteran. Right?” “Yes. I was in the US Air Force for 9 years.” “Wow. And you came out and blew the whistle on geoengineering, things that you witnessed were going on. Can you give us the real nutshell?” “Absolutely. Basically, I had heard of what many know as the term chemtrails. Um, and I worked in a job called bioenvironmental engineering, and I figured I thought that was insane. And why would we do something like that, modify the weather by using hazardous materials in our atmosphere. So and, actually, the process of trying to debunk it or disprove it, I realized it was actually coming right out of my office as I was 1 of the people that was approving the chemicals. And, um, it really shook the core of my oath, and I did a lot of sampling to a lot of investigation, and I blew the whistle and I got out. And I've now used my credentials, my oath, and my powers for good to help people understand it's very real. It's now openly admitted. There are multiple forms of weather modification” For the Notes that will 100% attempted to be added to this post, we already know you fact checkers say Chemtrails are a “conspiracy theory” and what we are looking at in the sky is really “water vapor” no matter what evidence is provided. There, I already provided your input, there is no need to add your context.

Wall Street Apes

2,756,604 views • 2 years ago