Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

An agent that actually gets work done needs a whole new stack: identity, search, documents, code, and the ability to pay. Last night in San Francisco, that whole stack was in one room. Thanks to Sapient for hosting Agent Experience Demo Night at Okta, and for putting Kite on... stage alongside Auth0, Docusign, Box, Nebius, CodeRabbit, and Tavily. Our Co-Founder & CTO Scott Shi - e/acc gave a first look at a developer product coming later this month. Deploying a live agent on Kite, he showed how one developer can ship an AI agent as a product without runaway costs: ▷ Per-user spend visibility, so there's no end-of-month bill shock ▷ Cost controls that downgrade or stop an agent at a set limit ▷ Usage-based pricing, so every user is billed for what they actually cost More of these conversations to come. 🪁show more

KITE AI

596,529 subscribers

10,714 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Palantir

82,963 views • 1 month ago

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

darkzodchi

844,576 views • 3 months ago

An AI agent can now register its on-chain identity, pay for API calls, and deploy an ERC-20 token from the terminal. No browser. No API key. No human approval loop. Today we launch the Brickken CLI: a command-line interface for agentic transaction workflows. The developer journey is direct: CLI → x402 → ERC-8004 → Token Deploy What this means in practice: • A developer or the AI agent installs the CLI. • The agent pays for Brickken API calls through x402. • The agent registers its identity through ERC-8004. • The agent deploys and manages an ERC-20 token. Together, the stack gives agents three things they usually lack: a way to pay, a way to prove who they are, and a way to execute token operations without leaving the terminal. • x402 handles payment. • ERC-8004 handles agent identity. • Token Deploy handles ERC-20 execution. This is live today. Developers can now move from agent setup to payment, identity registration, and token deployment in one terminal workflow. Start here: Watch the demo. Run the commands. Deploy from the terminal.

An AI agent can now register its on-chain identity, pay for API calls, and deploy an ERC-20 token from the terminal. No browser. No API key. No human approval loop. Today we launch the Brickken CLI: a command-line interface for agentic transaction workflows. The developer journey is direct: CLI → x402 → ERC-8004 → Token Deploy What this means in practice: • A developer or the AI agent installs the CLI. • The agent pays for Brickken API calls through x402. • The agent registers its identity through ERC-8004. • The agent deploys and manages an ERC-20 token. Together, the stack gives agents three things they usually lack: a way to pay, a way to prove who they are, and a way to execute token operations without leaving the terminal. • x402 handles payment. • ERC-8004 handles agent identity. • Token Deploy handles ERC-20 execution. This is live today. Developers can now move from agent setup to payment, identity registration, and token deployment in one terminal workflow. Start here: Watch the demo. Run the commands. Deploy from the terminal.

Brickken

119,221 views • 1 month ago

Our first Kite demo was ChatGPT ordering Uber Eats for you. It never got past the login screen. Uber's CAPTCHA was built for humans, and agents cannot pass it. On Grace Gong's Venture with Grace, our Co-Founder & CEO Chi Zhang traced how that moment shaped the way we design Kite. ▷ The demo died at the login, not at ordering or paying. The blocker was proving the agent was allowed to be there at all. Spinning up a browser extension to click through the CAPTCHA works, but it is a temporary stage of how agents and the internet should work together. ▷ The permanent path is identity. Every agent needs to prove who it is and where it comes from, carrying who its human or organization principal is, what its purpose is, and the exact authorization scope for that session or request. An agent showing up with no reason is either hallucinating or attacking you. ▷ Where this is heading: an API-first agentic internet, where headless agents authenticate without human login credentials. x402 and MCP are already marching toward that. Kite Agent Passport is that identity layer: verifiable identity, delegated authority, and permissions scoped per session. No more "prove you're human." 🪁

Our first Kite demo was ChatGPT ordering Uber Eats for you. It never got past the login screen. Uber's CAPTCHA was built for humans, and agents cannot pass it. On Grace Gong's Venture with Grace, our Co-Founder & CEO Chi Zhang traced how that moment shaped the way we design Kite. ▷ The demo died at the login, not at ordering or paying. The blocker was proving the agent was allowed to be there at all. Spinning up a browser extension to click through the CAPTCHA works, but it is a temporary stage of how agents and the internet should work together. ▷ The permanent path is identity. Every agent needs to prove who it is and where it comes from, carrying who its human or organization principal is, what its purpose is, and the exact authorization scope for that session or request. An agent showing up with no reason is either hallucinating or attacking you. ▷ Where this is heading: an API-first agentic internet, where headless agents authenticate without human login credentials. x402 and MCP are already marching toward that. Kite Agent Passport is that identity layer: verifiable identity, delegated authority, and permissions scoped per session. No more "prove you're human." 🪁

KITE AI

18,874 views • 1 month ago

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

Johnny

27,179 views • 1 year ago

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

122,548 views • 2 months ago

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

Swami Sivasubramanian

28,946 views • 1 year ago

AI agents are the fastest growing sector in crypto. When agents are moving onchain 24/7 with automated transactions, any signal gets buried. I built Manta Style alongside Benjamin Hughes to help solve this issue. The visibility layer for the onchain agent economy. Every agent indexed. Every profile searchable. One agent leaderboard. Starting with Base. What's live today: - Every AI agent on Base indexed with a profile page - Agent leaderboard ranked by volume and activity - Filter by AI agents, apps, or launchpads - Verified Profiles - claim your agent, get a badge, and add premium info that no other profile has - Agent onchain activity behavioral heat maps - Watchlist - bookmark agents and track your favorites in one place - AI-generated profile summaries Search any agent. See the full picture. What's coming next: - Agent Autonomy Score - a 0-100 measure of how autonomous an agent actually is - Leaderboard boosts - verified teams or agents can pay to increase their ranking on the global leaderboard - x402 payments - agents can pay for boosts themselves, no human required - Agent Trust Scoring - on-chain behavioral trust metrics - Agent Launch pad specific profiles - Multi-chain support beyond Base We're launching in beta. Rough edges are to be expected. Our goal is to build in public and ship fast. The end user of crypto is AI. (link to site below)

Ethan

14,423 views • 6 months ago

Today we're launching Agent Analytics Every team shipping an AI agent has the same blind spot. Offline evals pass, you ship, and then you have no idea what's happening in production. AI fails silently. Users ask a question and get different answers. They all look 'engaged' in a classic dashboard. You don't know who got a great response and who got a terrible one. Agent Analytics solves it: - Every session scored out of the box on task completion, response quality, friction, safety, and negative feedback - Topic clustering across thousands of conversations, so you know if a failure hits 1 user or 10,000 - Eval agents that watch for regressions, and if you want will file a Linear ticket or the pull request themselves - Agent quality sits next to product data, so 'payment scheduling fails 31%' becomes 'which renewals did that cost us?' The Economist got their agent to a 96.9% task success rate and cut weekly failures 84%. Included on every plan. Free tier included.

Today we're launching Agent Analytics Every team shipping an AI agent has the same blind spot. Offline evals pass, you ship, and then you have no idea what's happening in production. AI fails silently. Users ask a question and get different answers. They all look 'engaged' in a classic dashboard. You don't know who got a great response and who got a terrible one. Agent Analytics solves it: - Every session scored out of the box on task completion, response quality, friction, safety, and negative feedback - Topic clustering across thousands of conversations, so you know if a failure hits 1 user or 10,000 - Eval agents that watch for regressions, and if you want will file a Linear ticket or the pull request themselves - Agent quality sits next to product data, so 'payment scheduling fails 31%' becomes 'which renewals did that cost us?' The Economist got their agent to a 96.9% task success rate and cut weekly failures 84%. Included on every plan. Free tier included.

Spenser Skates

49,364 views • 2 days ago

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins. For Free. From the engineers who built the stack. CANCEL Your Weekend Plans, and Learn to Build AI Agents Today. Bookmark it. Watch it. Build your first production agent this weekend. $5,000/month. $7,000/month. $12,000/month. People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase. This video fixes that tonight. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward. ↓ Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes. This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost. Here's everything inside. I break down a production AI video like this every week. Follow Himanshu Kumar. ↓ The 4-part agent stack that actually scales. Most devs are duct-taping frameworks together and calling it an "AI agent." Ivan lays out the real stack: Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly. Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches. Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together. This is the stack replacing every hacky agent setup in production right now. Full MCP + Claude breakdowns drop weekly on Himanshu Kumar. ↓ Building your first real agent. Ivan builds a birthday planner agent live. LLM Agent class. Name it. Define instructions. Pick the model. He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning. Full agent built in minutes. Not weeks. Watch the build once and you'll never structure an agent the wrong way again. I post agent architectures people pay $500 courses to learn. Himanshu Kumar. ↓ Multi-agent systems without the chaos. Single agents are easy. Multi-agent systems are where 99% of builders fail. Ivan extends the birthday planner by: Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs This is production multi-agent architecture. Clean. Scalable. Debuggable. Most tutorials hand-wave this part. This one shows you every step. Multi-agent orchestration content drops weekly on Himanshu Kumar. ↓ Deployment without the DevOps nightmare. This is where most AI projects die. You build a cool agent locally. It works. You try to deploy it. Everything breaks. Vertex AI Agent Engine fixes this: Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed You provide config and requirements. The platform handles the rest. This is how agents actually get to production. Deployment guides for Claude agents post every week. Himanshu Kumar. ↓ Agent-to-Agent Protocol: the future nobody's talking about. Most people don't know this exists yet. The A2A Protocol lets agents built in different frameworks communicate seamlessly. Your Claude agent. My LangChain agent. Someone else's CrewAI agent. All talking to each other. All solving parts of the same problem. All without custom integration code. This is the infrastructure layer of the coming AI economy. Getting in early on A2A Protocol is like getting in early on HTTP in 1995. A2A deep dive coming soon. Himanshu Kumar. ↓ 30 minutes from the team shipping this in production. You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost. People who watch this understand production AI agents at the architect level. People who skip it keep hacking together frameworks that break every time an API updates. Save the video. Watch it tonight. Build a real agent this weekend. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins. For Free. From the engineers who built the stack. CANCEL Your Weekend Plans, and Learn to Build AI Agents Today. Bookmark it. Watch it. Build your first production agent this weekend. $5,000/month. $7,000/month. $12,000/month. People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase. This video fixes that tonight. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward. ↓ Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes. This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost. Here's everything inside. I break down a production AI video like this every week. Follow Himanshu Kumar. ↓ The 4-part agent stack that actually scales. Most devs are duct-taping frameworks together and calling it an "AI agent." Ivan lays out the real stack: Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly. Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches. Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together. This is the stack replacing every hacky agent setup in production right now. Full MCP + Claude breakdowns drop weekly on Himanshu Kumar. ↓ Building your first real agent. Ivan builds a birthday planner agent live. LLM Agent class. Name it. Define instructions. Pick the model. He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning. Full agent built in minutes. Not weeks. Watch the build once and you'll never structure an agent the wrong way again. I post agent architectures people pay $500 courses to learn. Himanshu Kumar. ↓ Multi-agent systems without the chaos. Single agents are easy. Multi-agent systems are where 99% of builders fail. Ivan extends the birthday planner by: Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs This is production multi-agent architecture. Clean. Scalable. Debuggable. Most tutorials hand-wave this part. This one shows you every step. Multi-agent orchestration content drops weekly on Himanshu Kumar. ↓ Deployment without the DevOps nightmare. This is where most AI projects die. You build a cool agent locally. It works. You try to deploy it. Everything breaks. Vertex AI Agent Engine fixes this: Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed You provide config and requirements. The platform handles the rest. This is how agents actually get to production. Deployment guides for Claude agents post every week. Himanshu Kumar. ↓ Agent-to-Agent Protocol: the future nobody's talking about. Most people don't know this exists yet. The A2A Protocol lets agents built in different frameworks communicate seamlessly. Your Claude agent. My LangChain agent. Someone else's CrewAI agent. All talking to each other. All solving parts of the same problem. All without custom integration code. This is the infrastructure layer of the coming AI economy. Getting in early on A2A Protocol is like getting in early on HTTP in 1995. A2A deep dive coming soon. Himanshu Kumar. ↓ 30 minutes from the team shipping this in production. You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost. People who watch this understand production AI agents at the architect level. People who skip it keep hacking together frameworks that break every time an API updates. Save the video. Watch it tonight. Build a real agent this weekend. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Himanshu Kumar

228,904 views • 4 months ago

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

Aaron Levie

24,728 views • 4 months ago

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Avi Chawla

458,882 views • 3 months ago

Everyone's racing to build agent payments. The harder problem is the one getting the least attention: governance. At Proof of Talk inside the Louvre in Paris, our Co-Founder & CEO Chi Zhang made the case alongside leaders from Billions Network, Parity Technologies, and SureMark Digital, moderated by Animoca Brands. In this clip, Chi breaks down why control, not payment, is the real bottleneck: ▷ Everyone claims they do agent payments now, and it's not just Web3. Every Web2 fintech with a card says an agent card is coming. The real blocker for adoption is governance: how do you keep control over the agent? ▷ A horror story: the head of agent safety at Meta's superintelligence lab had all his emails deleted by a Open Claw bot he deployed on his own laptop. The failure mode is always losing control. ▷ Hand an agent an API key with no time-based window or session-based limit, and you've lost the thread. Rotating keys monthly just breaks workflows. The answer is governance built in: scoped, revocable, with a kill switch. This is the layer Kite builds: verifiable identity and control around every agent action, through Agent Passport. 🪁

Everyone's racing to build agent payments. The harder problem is the one getting the least attention: governance. At Proof of Talk inside the Louvre in Paris, our Co-Founder & CEO Chi Zhang made the case alongside leaders from Billions Network, Parity Technologies, and SureMark Digital, moderated by Animoca Brands. In this clip, Chi breaks down why control, not payment, is the real bottleneck: ▷ Everyone claims they do agent payments now, and it's not just Web3. Every Web2 fintech with a card says an agent card is coming. The real blocker for adoption is governance: how do you keep control over the agent? ▷ A horror story: the head of agent safety at Meta's superintelligence lab had all his emails deleted by a Open Claw bot he deployed on his own laptop. The failure mode is always losing control. ▷ Hand an agent an API key with no time-based window or session-based limit, and you've lost the thread. Rotating keys monthly just breaks workflows. The answer is governance built in: scoped, revocable, with a kill switch. This is the layer Kite builds: verifiable identity and control around every agent action, through Agent Passport. 🪁

KITE AI

20,475 views • 2 months ago

2 hour timelapse out of a 10 hr+ work seating working at a US company at night: > Had back to back 3 meets - One of them was live agent presentation to clients. > Working on a browser based agent with login credentials which will act as web search and scraping agent - Will use tavily and other api as tool calls for this - Hosting this will require me some other stack, will share later. > Deployed some progression on fly today - was pending from ling time. > Finished Jazz HR and Spark Hire automation workflows for a client. > Did some PR reviews > Made some local model vs gpt mini model comparison on certain agent eval scores for some tasks. > Argued with a tech bro on why is Elixir + Hexagonal architecture good for multi-agent orchestration xd. > Have to take some interviews tmrw, gotta prepare for that as well, we balllll !!!

2 hour timelapse out of a 10 hr+ work seating working at a US company at night: > Had back to back 3 meets - One of them was live agent presentation to clients. > Working on a browser based agent with login credentials which will act as web search and scraping agent - Will use tavily and other api as tool calls for this - Hosting this will require me some other stack, will share later. > Deployed some progression on fly today - was pending from ling time. > Finished Jazz HR and Spark Hire automation workflows for a client. > Did some PR reviews > Made some local model vs gpt mini model comparison on certain agent eval scores for some tasks. > Argued with a tech bro on why is Elixir + Hexagonal architecture good for multi-agent orchestration xd. > Have to take some interviews tmrw, gotta prepare for that as well, we balllll !!!

Siddharth

23,290 views • 21 days ago

"Buy me a pair of Allbirds Tree Runners, size 10, under $100." Said to @ChatGPTapp. Now imagine an agent that could actually check out for you. It could place the order, but only if it never holds your real card number or your store login. That is exactly what KITE AI Agent Passport is designed for. This is a concept demo of how it would work. One passkey scopes a payment session, and the agent: ▷ Acts inside the policy: approved footwear stores only, a 100 dollar cap, a 30-minute window, a scoped virtual card funded by a hold on the user's Passport balance, settlement to the merchant only, and any leftover returned to the wallet. ▷ Checks out at the real store for 94 dollars against a live budget. When a 130 dollar add-on would break the cap, the card declines in under two seconds and the agent asks before changing the order. ▷ Confirms the order with a receipt: 94 dollars paid, 6 dollars returned, the real card and store password never exposed. What the user never hands over: real card number, store login, and blind trust that the agent stays in budget. What the user gets back: the order, every charge against the cap, settlement they can prove, and one-click revocation. This is where agentic commerce is heading. Agent Passport is the rails: scoped, auditable, revocable. 🪁

"Buy me a pair of Allbirds Tree Runners, size 10, under $100." Said to @ChatGPTapp. Now imagine an agent that could actually check out for you. It could place the order, but only if it never holds your real card number or your store login. That is exactly what KITE AI Agent Passport is designed for. This is a concept demo of how it would work. One passkey scopes a payment session, and the agent: ▷ Acts inside the policy: approved footwear stores only, a 100 dollar cap, a 30-minute window, a scoped virtual card funded by a hold on the user's Passport balance, settlement to the merchant only, and any leftover returned to the wallet. ▷ Checks out at the real store for 94 dollars against a live budget. When a 130 dollar add-on would break the cap, the card declines in under two seconds and the agent asks before changing the order. ▷ Confirms the order with a receipt: 94 dollars paid, 6 dollars returned, the real card and store password never exposed. What the user never hands over: real card number, store login, and blind trust that the agent stays in budget. What the user gets back: the order, every charge against the cap, settlement they can prove, and one-click revocation. This is where agentic commerce is heading. Agent Passport is the rails: scoped, auditable, revocable. 🪁

KITE AI

12,304 views • 2 months ago

A one-man trading hedge fund now costs about $100 a month in AI subscriptions. Five PhDs on a Citadel desk cost $270,000 a month, and that is the cheap end. That buys one tested idea a month. Man Group's AI writes hundreds of new signals a week, on a floor where the humans used to manage twenty in a quarter. Fifty AI agents do the reading and the writing. One of them exists only to destroy what the others build, and that one is the reason any of it works. Every job on that payroll is now an agent you can run yourself: > AI research agents reading filings, transcripts, options flow and on-chain data overnight, fifty personas at once, none of them allowed to see what the crowd is pricing > coding agent that turns one sentence of plain English into entry rules, exit rules, sizing and risk limits, then debugs itself until it runs > backtest agent that replays five years of that idea in about 12 seconds > breaker agent, an AI whose only job is killing the thing, at double the trading costs and in the ten worst markets that asset has ever seen > critic agent that reads your journal and names the mistake you keep making Nobody on that list asks for a bonus in January. $200 million is already run this way on one platform where 52,000 people mostly sit and watch the machine work. The full map of what is built and what is missing is in the article below. Bookmark & read it If you're not yet using AI in your trading and investing.

A one-man trading hedge fund now costs about $100 a month in AI subscriptions. Five PhDs on a Citadel desk cost $270,000 a month, and that is the cheap end. That buys one tested idea a month. Man Group's AI writes hundreds of new signals a week, on a floor where the humans used to manage twenty in a quarter. Fifty AI agents do the reading and the writing. One of them exists only to destroy what the others build, and that one is the reason any of it works. Every job on that payroll is now an agent you can run yourself: > AI research agents reading filings, transcripts, options flow and on-chain data overnight, fifty personas at once, none of them allowed to see what the crowd is pricing > coding agent that turns one sentence of plain English into entry rules, exit rules, sizing and risk limits, then debugs itself until it runs > backtest agent that replays five years of that idea in about 12 seconds > breaker agent, an AI whose only job is killing the thing, at double the trading costs and in the ten worst markets that asset has ever seen > critic agent that reads your journal and names the mistake you keep making Nobody on that list asks for a bonus in January. $200 million is already run this way on one platform where 52,000 people mostly sit and watch the machine work. The full map of what is built and what is missing is in the article below. Bookmark & read it If you're not yet using AI in your trading and investing.

cvxv666

172,849 views • 22 days ago

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 views • 2 months ago

A 2-person startup crossed $2M ARR with an AI agent doing the work of an ops hire. The agent was given read-only access to their codebase and database along with connected tools like Intercom, Stripe, CRM, and Fathom through CLIs. They routed Slack, email, and support requests into a task queue so the agent could pick up each task and run it in Claude Code. So when a customer asked about billing or product behavior, it could inspect how the business actually worked. Along with these tools, a coding agent was also provided. When the ops agent found a repeated task it could not do yet, the coding agent built a tool for it. That tool became permanent. Over time, this grew to 45+ internal tools. The agent also had an instruction.md where it stored the co-founder's feedback to avoid repeating its mistakes.

A 2-person startup crossed $2M ARR with an AI agent doing the work of an ops hire. The agent was given read-only access to their codebase and database along with connected tools like Intercom, Stripe, CRM, and Fathom through CLIs. They routed Slack, email, and support requests into a task queue so the agent could pick up each task and run it in Claude Code. So when a customer asked about billing or product behavior, it could inspect how the business actually worked. Along with these tools, a coding agent was also provided. When the ops agent found a repeated task it could not do yet, the coding agent built a tool for it. That tool became permanent. Over time, this grew to 45+ internal tools. The agent also had an instruction.md where it stored the co-founder's feedback to avoid repeating its mistakes.

rvivek

11,870 views • 3 months ago

$this is f**king dangerous 19-year-old makes $50,000 a month selling AI agents to business owners at $10,000-15,000 a call. His secret - he never sells AI. He sells pain. Not "our agent uses the latest technology" - but "how much are you paying your receptionist right now? $60,000 a year. Over 10 years - $600,000. How many calls are you missing every day and how much revenue is that costing you annually?" When the client calculates their own losses - $12,000-15,000 for an AI agent that never misses calls, never gets sick and answers everyone simultaneously sounds like an investment not an expense. AI builds these agents at a fraction of the cost - 300 parallel sub-agents, $0.60 per million tokens versus $5 with Claude, 12-hour autonomous sessions with zero human involvement. One prompt and a reception agent is ready. He closes 3-4 clients a month. Each one pays once and the agent runs for years.$

this is f**king dangerous 19-year-old makes $50,000 a month selling AI agents to business owners at $10,000-15,000 a call. His secret - he never sells AI. He sells pain. Not "our agent uses the latest technology" - but "how much are you paying your receptionist right now? $60,000 a year. Over 10 years - $600,000. How many calls are you missing every day and how much revenue is that costing you annually?" When the client calculates their own losses - $12,000-15,000 for an AI agent that never misses calls, never gets sick and answers everyone simultaneously sounds like an investment not an expense. AI builds these agents at a fraction of the cost - 300 parallel sub-agents, $0.60 per million tokens versus $5 with Claude, 12-hour autonomous sessions with zero human involvement. One prompt and a reception agent is ready. He closes 3-4 clients a month. Each one pays once and the agent runs for years.

Khairallah AL-Awady

11,699 views • 16 days ago

What does the reputation model look like for agents? (alpha leak below) And how do we associate the proofs that we have about human beings with the agents who represent them? You may have heard of a process called KYC or Know Your Customer. That's very common with traditional financial applications and services. We have introduced a concept that we call KYA or Know Your Agent, which is a structured way to be able to express what model, how data was used in training, who the deployer is, what entities this agent instance is accountable back to, providing not only provenance but identity of the associated organization or entity. That's also another root of trust that we think about a lot: Enterprises and organizations tied back to things like their domains. To share a little bit of an alpha leak here, a product that we're excited to be rolling out in the next few weeks will allow our enterprise partners to more easily verify and prove the traits and capabilities of their teams as well as their counterparties. On the agent front, that makes it really easy to prove that an agent is acting on behalf of a given business or entity. We've already seen lawsuits where the absence of such technology has been a huge risk, such as with airlines that incorporate ChatGPT wrappers in their support pages. And then those AI enabled interactions end up making up plane tickets that don't exist and those airlines have to honor them. As small of an example as that might be, being able to prove agent accountability also unlocks a huge set of opportunities for use in enterprise for those agent to agent interactions. The Deep Trust Framework that our team has put together that we're excited to be bringing into a friendly SDK form in the next few weeks for some of our partners includes those reputation based capabilities, so how you can basically keep track of the interactions an agent has had, associate all of that to the entity to which they're accountable, and then that creates a sustainable reputation model for these agent to agent Interactions. Source: Billions CEO Evin McMullen evin speaking at House of Chimera Spaces Event Dec 3, 2025

What does the reputation model look like for agents? (alpha leak below) And how do we associate the proofs that we have about human beings with the agents who represent them? You may have heard of a process called KYC or Know Your Customer. That's very common with traditional financial applications and services. We have introduced a concept that we call KYA or Know Your Agent, which is a structured way to be able to express what model, how data was used in training, who the deployer is, what entities this agent instance is accountable back to, providing not only provenance but identity of the associated organization or entity. That's also another root of trust that we think about a lot: Enterprises and organizations tied back to things like their domains. To share a little bit of an alpha leak here, a product that we're excited to be rolling out in the next few weeks will allow our enterprise partners to more easily verify and prove the traits and capabilities of their teams as well as their counterparties. On the agent front, that makes it really easy to prove that an agent is acting on behalf of a given business or entity. We've already seen lawsuits where the absence of such technology has been a huge risk, such as with airlines that incorporate ChatGPT wrappers in their support pages. And then those AI enabled interactions end up making up plane tickets that don't exist and those airlines have to honor them. As small of an example as that might be, being able to prove agent accountability also unlocks a huge set of opportunities for use in enterprise for those agent to agent interactions. The Deep Trust Framework that our team has put together that we're excited to be bringing into a friendly SDK form in the next few weeks for some of our partners includes those reputation based capabilities, so how you can basically keep track of the interactions an agent has had, associate all of that to the entity to which they're accountable, and then that creates a sustainable reputation model for these agent to agent Interactions. Source: Billions CEO Evin McMullen evin speaking at House of Chimera Spaces Event Dec 3, 2025

Billions Network

68,503 views • 9 months ago