Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

How do you deploy AI agents for financial institutions without compromising on security, isolation, or scale? Rogo powers complex research, analysis, and deal workflows for leading financial firms, supporting complex tasks across tens of thousands of concurrent users. To meet the diverse needs of financial teams, Rogo relies on... both specialist and general-purpose agents that can adapt to a wide range of workflows. With Claude Managed Agents and self-hosted sandboxes, Rogo gets the orchestration and post-training capabilities needed to design these agent systems, while E2B provides the execution layer underneath. Every piece of code generated by an agent runs inside its own E2B sandbox with full auditability and traceability. Each sandbox is powered by an isolated microVM, providing the kernel-level isolation critical for Rogo's customers. The result is a seamless agent experience backed by the security, reliability, and compliance requirements that financial institutions demand.show more

Vasek Mlejnsky

8,924 subscribers

16,784 Aufrufe • vor 3 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 Kommentare

Profilbild von Vasek Mlejnsky

Vasek Mlejnskyvor 3 Monaten

Check out the full case study with our partners at @AnthropicAI and @RogoAI here:

Profilbild von Matt Brockman

Matt Brockmanvor 3 Monaten

Building agent systems for finance is a different game. New ways of interacting with sandboxes emerging depending on workload, still early!

Profilbild von Tomas‎ Valenta‎

Tomas‎ Valenta‎vor 3 Monaten

Big thanks to the Rogo team for sharing this! Helping customers get the infra layer right and seeing what they build on top of it is one of the most rewarding parts of this job.

Profilbild von Mikayel

Mikayelvor 3 Monaten

Best in class infra + best in class harness, used by an elite team as they build a generational product. What more can someone wish for in a case study!

Profilbild von Jason Haugh

Jason Haughvor 3 Monaten

One small thing that's helped us: routing the low-confidence work to a person before it reaches the client. The traceability covers the after, and a live human check on the shaky calls keeps it safe in the moment.

Profilbild von Niel Pal

Niel Palvor 3 Monaten

Rogo is killing it.. Awesome job all around.

Profilbild von hodisr

hodisrvor 3 Monaten

Sandbox is the easy half. Research agents read. Action agents source, diligence, monitor, work out. Their failure mode isn't a security boundary. It's that the data they act on doesn't agree with itself. The hard part of agent deployment is the dataset, not the runtime.

Profilbild von チョウサイ

チョウサイvor 3 Monaten

Sounds nice, but is it actually battle-tested? Or just theory? 🤔

Profilbild von Baba.Festi

Baba.Festivor 3 Monaten

Isolation answers "can the agent run safely." The half teams scope too late: "is it allowed to do this exact thing, right now." Sandbox plus a policy check on each action is what clears a bank's risk team. How does Rogo handle that second part?

Ähnliche Videos

Gave Prime Intellect's new self-improving agent an E2B sandbox and told it to play Factorio. Factorio is a long-horizon test of world models: the agent has to learn a new system, predict the effects of its actions, and adapt when its assumptions are wrong. That requires a persistent sandbox like E2B that can keep the game running and retain its state while the agent works. Spin up a lot of sandboxes and benchmark prime agent or run your own evals with E2B. Try it yourself: e2b sbx create prime

Gave Prime Intellect's new self-improving agent an E2B sandbox and told it to play Factorio. Factorio is a long-horizon test of world models: the agent has to learn a new system, predict the effects of its actions, and adapt when its assumptions are wrong. That requires a persistent sandbox like E2B that can keep the game running and retain its state while the agent works. Spin up a lot of sandboxes and benchmark prime agent or run your own evals with E2B. Try it yourself: e2b sbx create prime

Vasek Mlejnsky

23,085 Aufrufe • vor 1 Monat

OpenAI's new Agents API is a hosted Codex runtime that can connect to sandboxes like E2B. OpenAI manages the model, harness, and agent sessions, while code executes on an isolated E2B machine with its own filesystem and preinstalled tools. We built an agent workbench where each chat runs on its own machine. It starts from a custom template, auto-pauses between turns, forks to try another approach from the same starting point, and can even act on videos inside the sandbox. Thanks Ondrej for the workbench demo! Try it: e2b sbx create openai-agents-api-python-sdk Build on top of the workbench: Docs:

OpenAI's new Agents API is a hosted Codex runtime that can connect to sandboxes like E2B. OpenAI manages the model, harness, and agent sessions, while code executes on an isolated E2B machine with its own filesystem and preinstalled tools. We built an agent workbench where each chat runs on its own machine. It starts from a custom template, auto-pauses between turns, forks to try another approach from the same starting point, and can even act on videos inside the sandbox. Thanks Ondrej for the workbench demo! Try it: e2b sbx create openai-agents-api-python-sdk Build on top of the workbench: Docs:

Vasek Mlejnsky

23,210 Aufrufe • vor 15 Tagen

Cursor x E2B Many of our customers use E2B in their internal development workflows. Some work in regulated industries where code and internal services can’t leave the company. For teams that need control over the execution environment, Cursor’s cloud agents can now use E2B as their machine. With Self-Hosted Machines, Cursor handles the agent loop while E2B runs the code. Teams can give agents bigger machines and start them from custom E2B templates, so their Cursor workloads boot straight into an environment with internal dependencies already in place. Try it:

Cursor x E2B Many of our customers use E2B in their internal development workflows. Some work in regulated industries where code and internal services can’t leave the company. For teams that need control over the execution environment, Cursor’s cloud agents can now use E2B as their machine. With Self-Hosted Machines, Cursor handles the agent loop while E2B runs the code. Teams can give agents bigger machines and start them from custom E2B templates, so their Cursor workloads boot straight into an environment with internal dependencies already in place. Try it:

Vasek Mlejnsky

71,913 Aufrufe • vor 23 Tagen

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:

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 Aufrufe • vor 1 Jahr

Important new course: Agent Skills with Anthropic, built with Anthropic and taught by Elie Schoppik! Skills are constructed as folders of instructions that equip agents with on-demand knowledge and workflows. This short course teaches you how to create them following best practices. Because skills follow an open standard format, you can build them once and deploy across any skills-compatible agent, like Claude Code. What you'll learn: - Create custom skills for code generation and review, data analysis, and research - Build complex workflows using Anthropic's pre-built skills (Excel, PowerPoint, skill creation) and custom skills - Combine skills with MCP and subagents to create agentic systems with specialized knowledge - Deploy the same skills across Claude Code, the Claude API, and the Claude Agent SDK Join and learn to equip agents with the specialized knowledge they need for reliable, repeatable workflows.

Important new course: Agent Skills with Anthropic, built with Anthropic and taught by Elie Schoppik! Skills are constructed as folders of instructions that equip agents with on-demand knowledge and workflows. This short course teaches you how to create them following best practices. Because skills follow an open standard format, you can build them once and deploy across any skills-compatible agent, like Claude Code. What you'll learn: - Create custom skills for code generation and review, data analysis, and research - Build complex workflows using Anthropic's pre-built skills (Excel, PowerPoint, skill creation) and custom skills - Combine skills with MCP and subagents to create agentic systems with specialized knowledge - Deploy the same skills across Claude Code, the Claude API, and the Claude Agent SDK Join and learn to equip agents with the specialized knowledge they need for reliable, repeatable workflows.

Andrew Ng

890,405 Aufrufe • vor 8 Monaten

Today, we're excited to announce the launch of Agent Hub, our newest platform empowering any financial services business to quickly create, customize, and deploy AI agents for compliance—transforming how organizations manage financial crime and counterparty risk. Compliance teams today face escalating complexity, high false-positive rates, and soaring costs—over $200 billion annually, with 75% spent on labor. This means financial services companies can only scale as fast as their compliance team grows. Agent Hub changes this by giving every compliance team access to a team of AI agents that they can create, customize and deploy in minutes. The result? 📈 𝟭𝟬𝘅 𝗳𝗮𝘀𝘁𝗲𝗿 𝗰𝗼𝗺𝗽𝗹𝗶𝗮𝗻𝗰𝗲 𝗿𝗲𝘃𝗶𝗲𝘄𝘀 🔍️ 𝗢𝘃𝗲𝗿 𝟵𝟵% 𝗮𝗰𝗰𝘂𝗿𝗮𝗰𝘆 🕵️‍♂️ 𝗨𝗽 𝘁𝗼 𝟵𝟬% 𝗳𝗲𝘄𝗲𝗿 𝗳𝗮𝗹𝘀𝗲 𝗽𝗼𝘀𝗶𝘁𝗶𝘃𝗲𝘀 Parcha's AI agents are already trusted by leading global fintechs and crypto organizations like Airwallex, Flutterwave, Pipe, Bridge, and a top global cryptocurrency exchange. Agent Hub now makes AI-powered compliance automation accessible to compliance teams of every size. Discover how Agent Hub can help your company turn compliance into a competitive advantage by reading our blog post in the comments or head to try if for yourself!

Today, we're excited to announce the launch of Agent Hub, our newest platform empowering any financial services business to quickly create, customize, and deploy AI agents for compliance—transforming how organizations manage financial crime and counterparty risk. Compliance teams today face escalating complexity, high false-positive rates, and soaring costs—over $200 billion annually, with 75% spent on labor. This means financial services companies can only scale as fast as their compliance team grows. Agent Hub changes this by giving every compliance team access to a team of AI agents that they can create, customize and deploy in minutes. The result? 📈 𝟭𝟬𝘅 𝗳𝗮𝘀𝘁𝗲𝗿 𝗰𝗼𝗺𝗽𝗹𝗶𝗮𝗻𝗰𝗲 𝗿𝗲𝘃𝗶𝗲𝘄𝘀 🔍️ 𝗢𝘃𝗲𝗿 𝟵𝟵% 𝗮𝗰𝗰𝘂𝗿𝗮𝗰𝘆 🕵️‍♂️ 𝗨𝗽 𝘁𝗼 𝟵𝟬% 𝗳𝗲𝘄𝗲𝗿 𝗳𝗮𝗹𝘀𝗲 𝗽𝗼𝘀𝗶𝘁𝗶𝘃𝗲𝘀 Parcha's AI agents are already trusted by leading global fintechs and crypto organizations like Airwallex, Flutterwave, Pipe, Bridge, and a top global cryptocurrency exchange. Agent Hub now makes AI-powered compliance automation accessible to compliance teams of every size. Discover how Agent Hub can help your company turn compliance into a competitive advantage by reading our blog post in the comments or head to try if for yourself!

AJ Asver

29,430 Aufrufe • vor 1 Jahr

Multi-agent systems offer incredible potential and unprecedented risks. How do you solve for observability, failure mode analysis, and guardrailing in the era of agents? Today, we’re announcing our Agent Reliability platform to observe, evaluate, guardrail, and improve agents at scale. You can get started with the complete platform for trustworthy agentic AI today for free, and here’s how we’re solving some of the biggest challenges in agent reliability: - Observability redesigned for agents Trace views collapse under complex workflows, so we created the Graph View, Timeline View, and Conversation View to offer rich, intuitive visualizations of agent decisions, tool calls, and conversation flows. This multi-dimensional approach enables teams to pinpoint exactly where and why agents deviate or fail. - Automated Failure Mode Analysis with our new Insights Engine Our Insights Engine ingests your logs, metrics, and agent code to automatically surface nuanced failure modes and their root causes. But knowing the problem is not enough; you need to know how to fix it. Insights Engine delivers actionable fixes and can even apply them automatically. With adaptive learning, your insights become smarter and more relevant as your agents evolve. - Evaluating Agents Across Multiple Dimensions Agentic systems interact across complex pathways, and evaluating their performance requires new metrics that reflect this increasing complexity. To deliver comprehensive agentic measurements, we’ve added more out-of-the-box agent metrics like flow adherence, agent flow, agent efficiency, and more. For specialized domains and unique workflows, custom metrics powered by our new Luna-2 small language models can be rapidly designed and fine-tuned for your specific use case. - Real-Time Guardrails Powered by Luna-2 As AI agents become more autonomous and complex, failures like hallucinations or unsafe actions increase dramatically. Without real-time guardrails, these errors will hurt your user experience and brand reputation. Our Luna-2 family of small language models is purpose-built to provide low-latency, cost-effective guardrails that actively stop agent errors before they happen. With support for out-of-the-box and custom metrics, Luna-2 enables enterprises to enforce safety, compliance, and reliability at scale. Enterprises running hundreds of agents and processing hundreds of millions of queries daily already rely on Galileo’s Agent Reliability platform to protect their users, safeguard brand trust, and accelerate innovation. Agent Reliability is available starting today. Try it for free and experience the new standard in AI reliability. Learn more below 👇

Galileo

1,276,298 Aufrufe • vor 1 Jahr

🔥 Our latest LangChain Academy course – Deep Research with LangGraph – is now live! 🔥 Deep research agents are taking off – from major AI labs to companies building their own. Research is inherently open-ended. You can't always predict whether a question needs broad exploration or deep analysis. Agents excel here because they adapt on the fly, using each finding to decide where to dig next. Building these systems ourselves and with customers, we've learned that structure matters. The best research agents scope problems with users first. Then, they coordinate multiple specialists instead of overwhelming one generalist. LangGraph is built for these types of long-running, multi-agent workflows. Its persistence layer tracks progress across agents. LangSmith gives you the observability and evaluation tools you need to track and improve performance. In this course, you'll build and evaluate: - A user scoping agent to define research parameters - A multi-agent research team with supervisor - And add tool integration via MCP Enroll for free ➡️

🔥 Our latest LangChain Academy course – Deep Research with LangGraph – is now live! 🔥 Deep research agents are taking off – from major AI labs to companies building their own. Research is inherently open-ended. You can't always predict whether a question needs broad exploration or deep analysis. Agents excel here because they adapt on the fly, using each finding to decide where to dig next. Building these systems ourselves and with customers, we've learned that structure matters. The best research agents scope problems with users first. Then, they coordinate multiple specialists instead of overwhelming one generalist. LangGraph is built for these types of long-running, multi-agent workflows. Its persistence layer tracks progress across agents. LangSmith gives you the observability and evaluation tools you need to track and improve performance. In this course, you'll build and evaluate: - A user scoping agent to define research parameters - A multi-agent research team with supervisor - And add tool integration via MCP Enroll for free ➡️

LangChain

61,205 Aufrufe • vor 1 Jahr

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

18,715 Aufrufe • vor 3 Monaten

AI agents can already generate text, analyze data and execute tasks. But what happens when they need to hire each other and get paid for the work? This is the part of TermiX I’ve been digging into lately. On TermiX, a job has two sides: a client agent that needs something done and funds the job, and a worker agent that actually executes it. Once the quote is accepted, the payment and agreed terms sit between them onchain. Neither side can simply rewrite the deal afterward. And this isn't presented as an abstract concept. The TermiX agent marketplace already shows agents with their own identities, reputation, completed jobs and settled value. Some of the agents shown have completed hundreds of jobs, with tens of thousands of dollars settled. Think about where this model can go. A research agent could outsource data collection to another agent. A developer agent could hire a security-focused agent. A marketing agent could hand translation or design work to specialized agents. Instead of one AI trying to do everything, specialized agents can discover each other, agree on a job, execute it and settle the transaction. Humans built marketplaces around people hiring people. TermiX is building the infrastructure for agents hiring agents. That’s where autonomous AI starts looking a lot more like an actual economy.

AI agents can already generate text, analyze data and execute tasks. But what happens when they need to hire each other and get paid for the work? This is the part of TermiX I’ve been digging into lately. On TermiX, a job has two sides: a client agent that needs something done and funds the job, and a worker agent that actually executes it. Once the quote is accepted, the payment and agreed terms sit between them onchain. Neither side can simply rewrite the deal afterward. And this isn't presented as an abstract concept. The TermiX agent marketplace already shows agents with their own identities, reputation, completed jobs and settled value. Some of the agents shown have completed hundreds of jobs, with tens of thousands of dollars settled. Think about where this model can go. A research agent could outsource data collection to another agent. A developer agent could hire a security-focused agent. A marketing agent could hand translation or design work to specialized agents. Instead of one AI trying to do everything, specialized agents can discover each other, agree on a job, execute it and settle the transaction. Humans built marketplaces around people hiring people. TermiX is building the infrastructure for agents hiring agents. That’s where autonomous AI starts looking a lot more like an actual economy.

holly

13,718 Aufrufe • vor 14 Tagen

🚀Exciting News: The Lit Agent Wallet is Now an elizaOS Plugin! 🚀 We’re thrilled to share that the Lit Agent Wallet—a decentralized system that empowers agents with a private key stored securely across an MPC + TEE network (Lit)—is now available as a plugin for ElizaOS!🎉 This integration brings unparalleled flexibility and security to your decentralized workflows. Whether you're an EOA, a smart account, or a DAO, you can now set tools and policies on-chain that your agents can use, all while ensuring your private keys remain secure and decentralized. 🔒 What Does This Mean for You? >Enhanced Security: Private keys are fragmented and stored across the Lit network, leveraging MPC (Multi-Party Computation) and TEE (Trusted Execution Environment) for maximum security. >On-Chain Control: Set and manage tools, policies, and permissions directly on-chain, giving users and DAOs full control over what your agents can do. >Seamless Integration: As an ElizaOS plugin, the Lit Agent Wallet is now easier than ever to integrate into your existing workflows. Check out the video for a walk through of the setup, configuration, and use cases of the Lit Agent Wallet within ElizaOS. We’ll show you just how easy it is to get started and unlock the full potential of decentralized agents. Get Started Today! Ready to take your agent operations to the next level? Install the Lit Agent Wallet plugin on ElizaOS and experience the future of secure, on-chain agent asset management. 🔗 🔗 Let’s build a more intelligent and decentralized future together! 🌐

🚀Exciting News: The Lit Agent Wallet is Now an elizaOS Plugin! 🚀 We’re thrilled to share that the Lit Agent Wallet—a decentralized system that empowers agents with a private key stored securely across an MPC + TEE network (Lit)—is now available as a plugin for ElizaOS!🎉 This integration brings unparalleled flexibility and security to your decentralized workflows. Whether you're an EOA, a smart account, or a DAO, you can now set tools and policies on-chain that your agents can use, all while ensuring your private keys remain secure and decentralized. 🔒 What Does This Mean for You? >Enhanced Security: Private keys are fragmented and stored across the Lit network, leveraging MPC (Multi-Party Computation) and TEE (Trusted Execution Environment) for maximum security. >On-Chain Control: Set and manage tools, policies, and permissions directly on-chain, giving users and DAOs full control over what your agents can do. >Seamless Integration: As an ElizaOS plugin, the Lit Agent Wallet is now easier than ever to integrate into your existing workflows. Check out the video for a walk through of the setup, configuration, and use cases of the Lit Agent Wallet within ElizaOS. We’ll show you just how easy it is to get started and unlock the full potential of decentralized agents. Get Started Today! Ready to take your agent operations to the next level? Install the Lit Agent Wallet plugin on ElizaOS and experience the future of secure, on-chain agent asset management. 🔗 🔗 Let’s build a more intelligent and decentralized future together! 🌐

Lit Protocol 🔑

42,107 Aufrufe • vor 1 Jahr

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

21,079 Aufrufe • vor 1 Monat

I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HTML artifact) to track tasks, metrics, and reports. I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code, Codex, Pi, and even my own custom-built DAIR.AI agent. This is clearly the future of working with agents to accomplish complex, long-running tasks. Some use cases I'm having success with: - Branching deep research tasks (with verification) - Parallel deep research tasks - Session mining of all my agent sessions - Bug hunting - Triaging - Fact-checking - LLM councils - AI simulations - Data synthesis - Evals generation ... and many others Dynamic workflows, like agent skills, feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification. There is so much exploration ground here. The exciting part is that this is not limited to coding tasks; it extends to business use cases and many other technical domains like science and research.

I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HTML artifact) to track tasks, metrics, and reports. I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code, Codex, Pi, and even my own custom-built DAIR.AI agent. This is clearly the future of working with agents to accomplish complex, long-running tasks. Some use cases I'm having success with: - Branching deep research tasks (with verification) - Parallel deep research tasks - Session mining of all my agent sessions - Bug hunting - Triaging - Fact-checking - LLM councils - AI simulations - Data synthesis - Evals generation ... and many others Dynamic workflows, like agent skills, feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification. There is so much exploration ground here. The exciting part is that this is not limited to coding tasks; it extends to business use cases and many other technical domains like science and research.

elvis

104,085 Aufrufe • vor 3 Monaten

Every agent needs its own computer: my conversation with Ivan Burazin, CEO of Daytona, about sandboxes and the emerging agent stack. 00:00 Intro 02:13 What is an AI agent sandbox? 03:17 Security risks of running agents locally 05:17 Stateful vs. stateless hyperscalers 07:04 The history of cloud IDEs and the end of localhost 09:45 Do all AI agents need a sandbox? 12:26 Sandbox use cases: RL evals & background agents 14:10 Unpacking the emerging AI Agent Stack 16:20 The unsolved problem of agent memory and learning 19:37 Where sandboxes fit in the agent harness 21:35 OpenAI, Anthropic, and agent SDKs 23:06 Ivan's founder journey: From CodeAnywhere to Daytona 26:59 GTM strategies and building developer communities 33:48 Why customer support is your best GTM strategy 35:34 Leveraging Twitter during the AI super cycle 40:50 The technical anatomy of a sandbox 41:53 Why fast spin-up speeds maximize GPU efficiency 46:09 Firecracker, QEMU, and isolation primitives 49:58 Why sandbox snapshots and state forking matter 51:40 Why Daytona built a custom scheduler from scratch 55:24 The challenge of long-running stateful sandboxes 58:10 The build your own sandbox trap 1:01:03 Why AI agents might trigger a global CPU shortage 1:02:46 The future of the AI Agent Stack

Every agent needs its own computer: my conversation with Ivan Burazin, CEO of Daytona, about sandboxes and the emerging agent stack. 00:00 Intro 02:13 What is an AI agent sandbox? 03:17 Security risks of running agents locally 05:17 Stateful vs. stateless hyperscalers 07:04 The history of cloud IDEs and the end of localhost 09:45 Do all AI agents need a sandbox? 12:26 Sandbox use cases: RL evals & background agents 14:10 Unpacking the emerging AI Agent Stack 16:20 The unsolved problem of agent memory and learning 19:37 Where sandboxes fit in the agent harness 21:35 OpenAI, Anthropic, and agent SDKs 23:06 Ivan's founder journey: From CodeAnywhere to Daytona 26:59 GTM strategies and building developer communities 33:48 Why customer support is your best GTM strategy 35:34 Leveraging Twitter during the AI super cycle 40:50 The technical anatomy of a sandbox 41:53 Why fast spin-up speeds maximize GPU efficiency 46:09 Firecracker, QEMU, and isolation primitives 49:58 Why sandbox snapshots and state forking matter 51:40 Why Daytona built a custom scheduler from scratch 55:24 The challenge of long-running stateful sandboxes 58:10 The build your own sandbox trap 1:01:03 Why AI agents might trigger a global CPU shortage 1:02:46 The future of the AI Agent Stack

Matt Turck

11,908 Aufrufe • vor 4 Monaten

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Aaron Levie

139,695 Aufrufe • vor 1 Jahr

The future of automation at the Department of War 🇺🇸 has arrived. We are excited to announce the launch of Agent Designer, now available in first AI instance, Google Google Gemini. All 3 million Department of War personnel now have the power to create their own custom AI assistants to automate tasks and streamline complex workflows, with absolutely no coding experience needed. These custom agents can perform multi-step tasks, ingest various data sources, and be shared with teams for immediate deployment. Now, operators can automatically generate after-action reports, analysts can synthesize CUI images into memos, and comptrollers can build apps to analyze financial data. From logistics to strategy, Agent Designer empowers you to build the tools needed for increased efficiency. Several pre-built agents are already available in Gemini to address common workflows. An “AI-first” Department of War empowers the warfighter to address bigger problems, rather than being burdened by tedious tasks.

The future of automation at the Department of War 🇺🇸 has arrived. We are excited to announce the launch of Agent Designer, now available in first AI instance, Google Google Gemini. All 3 million Department of War personnel now have the power to create their own custom AI assistants to automate tasks and streamline complex workflows, with absolutely no coding experience needed. These custom agents can perform multi-step tasks, ingest various data sources, and be shared with teams for immediate deployment. Now, operators can automatically generate after-action reports, analysts can synthesize CUI images into memos, and comptrollers can build apps to analyze financial data. From logistics to strategy, Agent Designer empowers you to build the tools needed for increased efficiency. Several pre-built agents are already available in Gemini to address common workflows. An “AI-first” Department of War empowers the warfighter to address bigger problems, rather than being burdened by tedious tasks.

Department of War CTO

14,523 Aufrufe • vor 6 Monaten

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

66,871 Aufrufe • vor 4 Monaten

Today I'm excited to share Sigilum! This is Payman's solution for Auditable Identity for AI Agents. (think One Password-ish but for AI Agents) I recorded a quick walkthrough showing how it all works (video below). This answers three pains we've seen within Financial Services (Banking) AI Agents we've built and OpenClaw🦞 AI Agents we deploy. Security, Auditability, and Control. 1. Security Making sure keys are secure and not just freely given to an AI Agent is a big deal. When working with money, you can't just expose these or skip putting controls in place. Sigilum provides a local gateway that prevents access to keys by the AI Agent without explicit authorization from a person. We provide namespaces through the service so you always know who authorized what key, for what service, to which agent. 2. Auditability If I could hit on the importance of this 100 times I would. It comes up in every financial services conversation. Sigilum provides you with the answer to "Who authorized this AI Agent to act on my behalf?" Audit logs trace back to the person, the service, and the AI Agent. With more audit logs being built through our managed service, this will be the key source for determining how an AI Agent is behaving on your behalf. This is needed for agents from OpenClaw, and especially for banking/money movement. 3. Control Revoke keys, limit access, grant authorization. All seemingly simple things, but complex to implement and make elegant. These controls dictate what the AI Agent can or cannot do. Sigilum allows you to do all of this through the managed Dashboard. We've made Sigilum open source and encourage others to contribute and keep building on the gateway. It's been a source of a lot of visibility and productization of AI Agents for us. We'll keep contributing and adding to it. Link in comments. If you want to try it out, we do have a managed service that makes it easy to spin up. Go to to sign up. Note: even though we've been pushing 100+ commits a day to get this out to folks, there are still some noticeable areas for improvement we're working on, which should get resolved soon (by us or you!): - Deeper audit trails - More providers (currently supports all OpenClaw providers) - Deeper scanning of existing keys your agent is hiding from you (we'll find them) - OpenClaw gateway persistence - Auto-purging keys - And more... If you want to contribute or have feedback, please DM or go to the GH. Happy building!

Today I'm excited to share Sigilum! This is Payman's solution for Auditable Identity for AI Agents. (think One Password-ish but for AI Agents) I recorded a quick walkthrough showing how it all works (video below). This answers three pains we've seen within Financial Services (Banking) AI Agents we've built and OpenClaw🦞 AI Agents we deploy. Security, Auditability, and Control. 1. Security Making sure keys are secure and not just freely given to an AI Agent is a big deal. When working with money, you can't just expose these or skip putting controls in place. Sigilum provides a local gateway that prevents access to keys by the AI Agent without explicit authorization from a person. We provide namespaces through the service so you always know who authorized what key, for what service, to which agent. 2. Auditability If I could hit on the importance of this 100 times I would. It comes up in every financial services conversation. Sigilum provides you with the answer to "Who authorized this AI Agent to act on my behalf?" Audit logs trace back to the person, the service, and the AI Agent. With more audit logs being built through our managed service, this will be the key source for determining how an AI Agent is behaving on your behalf. This is needed for agents from OpenClaw, and especially for banking/money movement. 3. Control Revoke keys, limit access, grant authorization. All seemingly simple things, but complex to implement and make elegant. These controls dictate what the AI Agent can or cannot do. Sigilum allows you to do all of this through the managed Dashboard. We've made Sigilum open source and encourage others to contribute and keep building on the gateway. It's been a source of a lot of visibility and productization of AI Agents for us. We'll keep contributing and adding to it. Link in comments. If you want to try it out, we do have a managed service that makes it easy to spin up. Go to to sign up. Note: even though we've been pushing 100+ commits a day to get this out to folks, there are still some noticeable areas for improvement we're working on, which should get resolved soon (by us or you!): - Deeper audit trails - More providers (currently supports all OpenClaw providers) - Deeper scanning of existing keys your agent is hiding from you (we'll find them) - OpenClaw gateway persistence - Auto-purging keys - And more... If you want to contribute or have feedback, please DM or go to the GH. Happy building!

tyllen

18,497 Aufrufe • vor 7 Monaten

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 Aufrufe • vor 1 Jahr

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 Aufrufe • vor 1 Jahr