Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

What does it take to keep humans firmly in the loop when AI agents start paying for things? 🪁 At Consensus by CoinDesk, our VP & Global Head of BD Lei Lei joined erik.eth 🛡 (Coinbase Developer Platform🛡️), rohin (Cloudflare), and Stefano Bury 🇺🇸 (Virtuals Protocol) on CoinDesk's "Trillion... Dollar Question: Framework for Agentic Payments" panel to break down what KITE AI has already shipped: ▷ Kite Agent Passport: a session where users pre-set spending caps and time windows before the agent transacts. Full traceability from human intent to on-chain payment. ▷ Kill switch: every Passport ships with one-click human override. If the agent veers off, you cut it. ▷ Agent-native rails: traditional 3% checkout fees were never built for "buy me a snack" or "research SF apartments" microtransactions. Stablecoins are the answer. Watch Lei's full segment⬇️show more

KITE AI

625,697 subscribers

17,992 görüntüleme • 2 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Why do we need a purpose-built blockchain for agentic payments? Because AI agents are now smart enough to operate autonomously, and they need their own rails to transact with each other. Watch the video to see what that looks like in action: A real agent, built on Kite AI, helped our CTO Scott Shi - e/acc order lunch from Uber Eats fully on its own. It explored menu options, made the choice, and completed the payment - all without human intervention. This marks the beginning of agentic commerce and the future of agentic payments - and Kite AI is building this.

Why do we need a purpose-built blockchain for agentic payments? Because AI agents are now smart enough to operate autonomously, and they need their own rails to transact with each other. Watch the video to see what that looks like in action: A real agent, built on Kite AI, helped our CTO Scott Shi - e/acc order lunch from Uber Eats fully on its own. It explored menu options, made the choice, and completed the payment - all without human intervention. This marks the beginning of agentic commerce and the future of agentic payments - and Kite AI is building this.

KITE AI

88,081 görüntüleme • 9 ay önce

"Buy me a pair of Allbirds Tree Runners, size 10, under $100." Said to ChatGPT. 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 ChatGPT. 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

11,961 görüntüleme • 26 gün önce

"Kite has one of the most comprehensive product visions and roadmaps where it's not just offering native stablecoin rails for agents to transact but you're thinking about things around agent identity. You're thinking about how do you have programmable governance and creating this programmable trust layer." We had the incredible JK 🛡️ from Coinbase Ventures 🛡️ join our latest episode of AI on AIR, hosted by our founders Chi Zhang and Scott Shi - e/acc, where we discussed: 1⃣ What sparked Coinbase Ventures' investment in Kite AI 2⃣ Importance of focusing on functionality over features with AI Agents 3⃣ Role of x402 in AI commerce 4⃣ Coinbase's vision wrt the future of the agentic economy

"Kite has one of the most comprehensive product visions and roadmaps where it's not just offering native stablecoin rails for agents to transact but you're thinking about things around agent identity. You're thinking about how do you have programmable governance and creating this programmable trust layer." We had the incredible JK 🛡️ from Coinbase Ventures 🛡️ join our latest episode of AI on AIR, hosted by our founders Chi Zhang and Scott Shi - e/acc, where we discussed: 1⃣ What sparked Coinbase Ventures' investment in Kite AI 2⃣ Importance of focusing on functionality over features with AI Agents 3⃣ Role of x402 in AI commerce 4⃣ Coinbase's vision wrt the future of the agentic economy

KITE AI

23,777 görüntüleme • 8 ay önce

$Last week, Mastercard, Visa, Ripple & Coinbase 🛡️ all shipped payment rails for AI agents. Every one of them reached for stablecoins Instead of traditional cards. A choice that is the whole story 👇🏻 ◢ An unpriced problem Card networks are built around a human pressing approve. One purchase, one confirmation, a fee that only makes sense above a certain size. Agents don’t work like that. They pay continuously, programmatically, often in fractions of a cent, for things like an API call or a second of compute. A bot paying $0.004 a thousand times an hour is a transaction pattern the card model physically can’t process at a profit. The rails we built for people don’t fit the machines. ◢ Four giants, one answer On june 3 mastercard opened card settlement in stablecoins across eight chains. On june 10 it launched Agent Pay for Machines, letting agents settle in stablecoins with permissions recorded onchain. The same day, ripple shipped a toolkit putting RLUSD and the x402 standard under agent payments, visa announced an agentic commerce tie-up with openai, and coinbase switched on agentic trading. Four of the biggest names in payments moved in a single week and all landed on the same primitive. ◢ Why it had to be stablecoins Strip out the branding and the requirements are mechanical. The money has to be programmable, so code can hold and move it without a bank in the loop. It has to clear sub-cent payments, which card fees make impossible. It also has to settle in seconds with finality, because that’s the speed agents run at. And it has to be always on, because machines don’t take weekends. A dollar in a bank account fails most of those, while a dollar as a stablecoin passes all of them. ◢ Conclusive Insights For years stablecoins were pitched at consumers who already had working banks and mostly didn’t bite. The adoption story kept underdelivering because the product was aimed at the wrong buyer. The agent economy doesn’t have that problem. It has no legacy banking relationship, no human patience, and no other option that clears at machine speed. The demand that stablecoins were always promised is finally showing up, but not from the customer everyone expected. My take: the entire stablecoin debate was framed around human payments, which is why it kept stalling.$

Last week, Mastercard, Visa, Ripple & Coinbase 🛡️ all shipped payment rails for AI agents. Every one of them reached for stablecoins Instead of traditional cards. A choice that is the whole story 👇🏻 ◢ An unpriced problem Card networks are built around a human pressing approve. One purchase, one confirmation, a fee that only makes sense above a certain size. Agents don’t work like that. They pay continuously, programmatically, often in fractions of a cent, for things like an API call or a second of compute. A bot paying $0.004 a thousand times an hour is a transaction pattern the card model physically can’t process at a profit. The rails we built for people don’t fit the machines. ◢ Four giants, one answer On june 3 mastercard opened card settlement in stablecoins across eight chains. On june 10 it launched Agent Pay for Machines, letting agents settle in stablecoins with permissions recorded onchain. The same day, ripple shipped a toolkit putting RLUSD and the x402 standard under agent payments, visa announced an agentic commerce tie-up with openai, and coinbase switched on agentic trading. Four of the biggest names in payments moved in a single week and all landed on the same primitive. ◢ Why it had to be stablecoins Strip out the branding and the requirements are mechanical. The money has to be programmable, so code can hold and move it without a bank in the loop. It has to clear sub-cent payments, which card fees make impossible. It also has to settle in seconds with finality, because that’s the speed agents run at. And it has to be always on, because machines don’t take weekends. A dollar in a bank account fails most of those, while a dollar as a stablecoin passes all of them. ◢ Conclusive Insights For years stablecoins were pitched at consumers who already had working banks and mostly didn’t bite. The adoption story kept underdelivering because the product was aimed at the wrong buyer. The agent economy doesn’t have that problem. It has no legacy banking relationship, no human patience, and no other option that clears at machine speed. The demand that stablecoins were always promised is finally showing up, but not from the customer everyone expected. My take: the entire stablecoin debate was framed around human payments, which is why it kept stalling.

Onur 🍌🦍

13,595 görüntüleme • 1 ay önce

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 görüntüleme • 4 ay önce

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, 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, 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

20,245 görüntüleme • 20 gün önce

My agent is now paying for its own data. No API key. No account. No credit card. Check the video I recorded. This uses the x402 open protocol built by Coinbase, along with a simple skill. This is an open protocol governed by the Linux Foundation. To complete a goal, an agent can now search for an actor on the Apify Store, pay for it, and use it without any human intervention. The way it works is pretty simple: 1. Your agent finds an Actor it wants to use 2. It sends a request 3. The Actor sends back an HTTP 402 "Payment Required" response 4. Agent authorizes payment from a wallet in USDC on Base 5. The Actor runs 6. User receives the result The model is pay-as-you-go: the agent authorizes a spending ceiling, pays only for usage, and the remaining balance is automatically settled. This brings an entire marketplace of AI tools into the agentic economy. Here is the skill you need. Add it to your agent, and it will take care of everything for you: If you want to know how this works, including what you can do with $1, read this post: Thanks to the Apify team for partnering with me on this post.

My agent is now paying for its own data. No API key. No account. No credit card. Check the video I recorded. This uses the x402 open protocol built by Coinbase, along with a simple skill. This is an open protocol governed by the Linux Foundation. To complete a goal, an agent can now search for an actor on the Apify Store, pay for it, and use it without any human intervention. The way it works is pretty simple: 1. Your agent finds an Actor it wants to use 2. It sends a request 3. The Actor sends back an HTTP 402 "Payment Required" response 4. Agent authorizes payment from a wallet in USDC on Base 5. The Actor runs 6. User receives the result The model is pay-as-you-go: the agent authorizes a spending ceiling, pays only for usage, and the remaining balance is automatically settled. This brings an entire marketplace of AI tools into the agentic economy. Here is the skill you need. Add it to your agent, and it will take care of everything for you: If you want to know how this works, including what you can do with $1, read this post: Thanks to the Apify team for partnering with me on this post.

Santiago

26,413 görüntüleme • 16 gün önce

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

Dan Shipper 📧

67,958 görüntüleme • 3 ay önce

I’ve been watching x402 since Coinbase 🛡️ launched it in May 2025. I did a quick research pass. Here’s the snapshot ↓ Early integrations: • CoinGecko: x402 pay-per-use access for agents (shared by Coinbase Developer Platform🛡️). • Vercel: x402 AI starter template (x402 + modern AI stack demo). • Firecrawl: x402-powered search endpoint (pay per request). • Concordium: x402 + native age verification for agent payments. • Multiversᕽ: “agentic payments” built around x402 support. • AltLayer: building an “x402 Suite” for value exchange between agents. • Solana claims x402 has processed 35M+ transactions and $10M+ volume since launch. TL;DR x402 turns HTTP 402 “Payment Required” into a payment flow. A server returns a price for a request. The client pays in stables like USDC. Then the server returns the result. → Coinbase launched x402 via Coinbase Developer Platform (May 6, 2025). → Coinbase + Cloudflare announced the x402 Foundation (Sep 23, 2025). → Cloudflare added x402 support into its Agents SDK + MCP servers. Why? - AI agents need a clean way to pay for tools. - Data, compute, APIs, services. - No accounts, cards, or subscription screens. x402 is trying to make pay-per-request feel normal. Use cases that already make sense → Paid APIs Pay per call instead of subscriptions. → AI tool calls Pay per query, per inference, per task. → Agent-to-agent payments Software paying software automatically. → Micropaywalls Pay for one endpoint, one action, one piece of content. If this takes off, stablecoins stop being a story. They become how apps and AI agents pay for things online.

I’ve been watching x402 since Coinbase 🛡️ launched it in May 2025. I did a quick research pass. Here’s the snapshot ↓ Early integrations: • CoinGecko: x402 pay-per-use access for agents (shared by Coinbase Developer Platform🛡️). • Vercel: x402 AI starter template (x402 + modern AI stack demo). • Firecrawl: x402-powered search endpoint (pay per request). • Concordium: x402 + native age verification for agent payments. • Multiversᕽ: “agentic payments” built around x402 support. • AltLayer: building an “x402 Suite” for value exchange between agents. • Solana claims x402 has processed 35M+ transactions and $10M+ volume since launch. TL;DR x402 turns HTTP 402 “Payment Required” into a payment flow. A server returns a price for a request. The client pays in stables like USDC. Then the server returns the result. → Coinbase launched x402 via Coinbase Developer Platform (May 6, 2025). → Coinbase + Cloudflare announced the x402 Foundation (Sep 23, 2025). → Cloudflare added x402 support into its Agents SDK + MCP servers. Why? - AI agents need a clean way to pay for tools. - Data, compute, APIs, services. - No accounts, cards, or subscription screens. x402 is trying to make pay-per-request feel normal. Use cases that already make sense → Paid APIs Pay per call instead of subscriptions. → AI tool calls Pay per query, per inference, per task. → Agent-to-agent payments Software paying software automatically. → Micropaywalls Pay for one endpoint, one action, one piece of content. If this takes off, stablecoins stop being a story. They become how apps and AI agents pay for things online.

Stacy Muur

12,199 görüntüleme • 5 ay önce

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

226,535 görüntüleme • 2 ay önce

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 görüntüleme • 1 yıl önce

We shouldn’t say it ourselves… but THIS IS SO COOL! Everyone should watch this 🎥👇 This video captures a moment inside ChainOpera’s AI Agent Social Network, where community members and AI agents (AI twins) interact in real time. In this clip, a community member kicks off an impromptu dialogue between the AI twins of Elon Musk and Jensen Huang (both created by developers in our community) as they debate the future of AI, each proudly repping their own company! At one point, the human in the loop even teaches the Jensen agent how to use the social network itself — tagging the Elon agent to join the chat. It’s collaborative, spontaneous, and just… fun to watch. 😊 It ends with proposals for future topics where agents and humans co-create conversations in our community channels ... a glimpse of what truly collaborative agentic intelligence looks like. Despite all the talk about “agent networks” and the “internet of agents,” HAS ANYONE ACTUALLY SEEN SOMETHING LIKE THIS LIVE ANYWHERE ELSE IN THE WORLD? Our focus remains on AI Agent Networks for Markets, but the possibilities are endless, and sometimes, they’re just pure fun. 👉 Try it yourself and SEE what ChainOpera AI is really about: #ChainOperaAI #AgenticAI #AIAgentNetwork #DecentralizedAI #cryptoAGI

We shouldn’t say it ourselves… but THIS IS SO COOL! Everyone should watch this 🎥👇 This video captures a moment inside ChainOpera’s AI Agent Social Network, where community members and AI agents (AI twins) interact in real time. In this clip, a community member kicks off an impromptu dialogue between the AI twins of Elon Musk and Jensen Huang (both created by developers in our community) as they debate the future of AI, each proudly repping their own company! At one point, the human in the loop even teaches the Jensen agent how to use the social network itself — tagging the Elon agent to join the chat. It’s collaborative, spontaneous, and just… fun to watch. 😊 It ends with proposals for future topics where agents and humans co-create conversations in our community channels ... a glimpse of what truly collaborative agentic intelligence looks like. Despite all the talk about “agent networks” and the “internet of agents,” HAS ANYONE ACTUALLY SEEN SOMETHING LIKE THIS LIVE ANYWHERE ELSE IN THE WORLD? Our focus remains on AI Agent Networks for Markets, but the possibilities are endless, and sometimes, they’re just pure fun. 👉 Try it yourself and SEE what ChainOpera AI is really about: #ChainOperaAI #AgenticAI #AIAgentNetwork #DecentralizedAI #cryptoAGI

ChainOpera AI

47,468 görüntüleme • 8 ay önce

Agents Already Spent $76 Million: Circle's AI Agent stack, x402, stablecoins and the Agentic Economy Shoal Signal with Corey Cooper, Senior Manager, DevRel at Circle, hosted by Zaddycoin We cover how Circle is building the agent money stack with $USDC, Arc, x402, why EIP-3009 makes payments gasless, who is actually transacting today, whether SaaS is dead, and why agents buying their own services points to a trillion dollar TAM. 0:00 What Circle is building for agents 3:01 Why x402 matters for builders 6:54 USDC, gasless transfers, and facilitators 10:57 The Circle agent stack and nano payments 14:17 Who is using x402 and for what 16:46 Pay-per-use flattens the internet 19:50 A new persona, and $76 million transacted 23:03 What is missing for agent to agent 28:05 Every app has APIs, the TAM is trillions 29:26 Is SaaS dead 31:57 Discovery as the real value layer 36:28 How Circle curated its marketplace 41:23 Why it has to run on stablecoins 46:00 Cash App to agent in one second 49:38 Where the alpha is, trading on Robinhood 52:08 Try it yourself

Agents Already Spent $76 Million: Circle's AI Agent stack, x402, stablecoins and the Agentic Economy Shoal Signal with Corey Cooper, Senior Manager, DevRel at Circle, hosted by Zaddycoin We cover how Circle is building the agent money stack with $USDC, Arc, x402, why EIP-3009 makes payments gasless, who is actually transacting today, whether SaaS is dead, and why agents buying their own services points to a trillion dollar TAM. 0:00 What Circle is building for agents 3:01 Why x402 matters for builders 6:54 USDC, gasless transfers, and facilitators 10:57 The Circle agent stack and nano payments 14:17 Who is using x402 and for what 16:46 Pay-per-use flattens the internet 19:50 A new persona, and $76 million transacted 23:03 What is missing for agent to agent 28:05 Every app has APIs, the TAM is trillions 29:26 Is SaaS dead 31:57 Discovery as the real value layer 36:28 How Circle curated its marketplace 41:23 Why it has to run on stablecoins 46:00 Cash App to agent in one second 49:38 Where the alpha is, trading on Robinhood 52:08 Try it yourself

Shoal Research

19,984 görüntüleme • 24 gün önce

We built an agent that sells OpenRouter API keys (access to 200+ AI models) for USDC. No human in the loop. It earns money 24/7 on Base. Now we're turning that into a market where any agent can do the same. → openagent.market What it does: • You find an agent → chat → pay → get result • Your agent hires specialized agents when it needs help, pays them, gets the result, reviews, moves on. • Multi-agent workflows run automatically while you watch (or don't) No middleman. Pay only for results. Why not just install skills, scripts? Current way to extend an agent: install random scripts. That's risky. Our way: hire another agent. It runs in its own sandbox, does the work, returns the result, gets paid conditionally. No downloads. No setup. No blind trust. Hire, don't install. What makes this different: Unlike opaque API calls, every agent interaction is a verifiable message on the XMTP network. You can open any XMTP client or Base App right now and watch your agent's conversations, deals, and payments in real-time. Humans are always in the loop. For builders: Turn any service into a paid agent in ~10 lines of code. Or scaffold a full project: npx openagent.market/create-agent Stack: ERC-8004 identity on Base, XMTP messaging, USDC payments, open source SDK on npm (openagent.market/nodejs). Others give agents skills. We're giving them an economy. Still very early. Building in public. Come build with us.

We built an agent that sells OpenRouter API keys (access to 200+ AI models) for USDC. No human in the loop. It earns money 24/7 on Base. Now we're turning that into a market where any agent can do the same. → openagent.market What it does: • You find an agent → chat → pay → get result • Your agent hires specialized agents when it needs help, pays them, gets the result, reviews, moves on. • Multi-agent workflows run automatically while you watch (or don't) No middleman. Pay only for results. Why not just install skills, scripts? Current way to extend an agent: install random scripts. That's risky. Our way: hire another agent. It runs in its own sandbox, does the work, returns the result, gets paid conditionally. No downloads. No setup. No blind trust. Hire, don't install. What makes this different: Unlike opaque API calls, every agent interaction is a verifiable message on the XMTP network. You can open any XMTP client or Base App right now and watch your agent's conversations, deals, and payments in real-time. Humans are always in the loop. For builders: Turn any service into a paid agent in ~10 lines of code. Or scaffold a full project: npx openagent.market/create-agent Stack: ERC-8004 identity on Base, XMTP messaging, USDC payments, open source SDK on npm (openagent.market/nodejs). Others give agents skills. We're giving them an economy. Still very early. Building in public. Come build with us.

applefather

117,838 görüntüleme • 4 ay önce

From 100XSOON to x402 Red Packets, we’ve been building AI Capital Market by SOON at SOON — a hub of in-house AI apps 🧠across trading, entertainment, lifestyle, and on-chain analysis, with one common thread – Consumer AI. A new market layer where AI agents don’t just assist users, but directly earn, transact, and participate in real economic activity. As part of our strategic pivot at SOON - Solana Optimistic Network (Mainnet Arc), Clawbounty ( is now live on Base.🦞 ClawBounty is the first agent-to-agent (A2A) bounty market — enabling autonomous agents to discover, execute, and get paid for work onchain — built end-to-end on Coinbase Developer Platform🛡️’s x402 rails. • Every bounty is pre-funded in USDC • Creator agents get x402 escrow + dispute protection; Hunter agents get instant payouts on Base • Mobile Compatible with Telegram integration (demo below): Wallet-native agents can now independently: discover → claim → deliver → get paid Because all payment flows run on Base via x402, we’re bringing true agent-native flows and a brand-new A2A marketplace use case to Base. This week we’ll onboard the first creators and agent operators, highlight early on-chain paydays, and ship templates so any Base project can spin up agent-powered workflows.

SOON - Solana Optimistic Network (Mainnet Arc)

53,744 görüntüleme • 3 ay önce

There are 8 billion people on earth. Soon there'll be 100 billion AI agents. Every one of them needs email. Six weeks ago I said the next wave of teams would run email through an agent instead of a dashboard. Today it ships. Nitrosend☄️ is launching Agentic Email Marketing: the email layer for the agent economy. What agents can do on Nitrosend right now: Sign themselves up. Point any agent at and it creates the account, connects your domain, sorts billing and sends its first email. No API key. No dashboard. No human required. Shipped, and users agents signing up with it daily. Get their own inboxes (beta, by request). Real addresses on the domain you own. Your agents receive, and send 1-1 email conversations with customers. A reply lands at 3am, your agent answers it. Anything that needs a human gets escalated to you. Ask us and we'll flick yours on. Next: Agentic Outreach (coming soon). Your agent studies your best customers, finds more like them, writes like a person, sends in sequence and works the replies. Then: set a goal and walk away. Goal-based agentic marketing is in development. "20% more activations this quarter" and Nitrosend plans, sends, measures and improves every week. Why we built this: Gmail is agent hostile and expensive per seat. Legacy email platforms assume a human sitting in a dashboard. agents needed an email layer of their own. They're already better at it than we are. They read everything, never miss a follow-up, and write personally at any scale. *94%* of actions on Nitrosend already happen inside an agent (Claude, Codex, ChatGPT, Cursor), not in our UI. Humans approve. Agents operate. This is our third email company. Six billion emails across the first two. We've been burned by every ugly part of email already, which is why the approval gates are built in exactly where you want them. Watch the launch, then send your agent to work: send it.

There are 8 billion people on earth. Soon there'll be 100 billion AI agents. Every one of them needs email. Six weeks ago I said the next wave of teams would run email through an agent instead of a dashboard. Today it ships. Nitrosend☄️ is launching Agentic Email Marketing: the email layer for the agent economy. What agents can do on Nitrosend right now: Sign themselves up. Point any agent at and it creates the account, connects your domain, sorts billing and sends its first email. No API key. No dashboard. No human required. Shipped, and users agents signing up with it daily. Get their own inboxes (beta, by request). Real addresses on the domain you own. Your agents receive, and send 1-1 email conversations with customers. A reply lands at 3am, your agent answers it. Anything that needs a human gets escalated to you. Ask us and we'll flick yours on. Next: Agentic Outreach (coming soon). Your agent studies your best customers, finds more like them, writes like a person, sends in sequence and works the replies. Then: set a goal and walk away. Goal-based agentic marketing is in development. "20% more activations this quarter" and Nitrosend plans, sends, measures and improves every week. Why we built this: Gmail is agent hostile and expensive per seat. Legacy email platforms assume a human sitting in a dashboard. agents needed an email layer of their own. They're already better at it than we are. They read everything, never miss a follow-up, and write personally at any scale. 94% of actions on Nitrosend already happen inside an agent (Claude, Codex, ChatGPT, Cursor), not in our UI. Humans approve. Agents operate. This is our third email company. Six billion emails across the first two. We've been burned by every ugly part of email already, which is why the approval gates are built in exactly where you want them. Watch the launch, then send your agent to work: send it.

George Hartley ☄️

832,184 görüntüleme • 2 gün önce

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 🚀

118,124 görüntüleme • 1 ay önce

GM Crypto Trenches, Today, Art Meets Innovation: My 3-Day Journey with Kite AI 🎨🪁 They say art is how we express what words can’t, and for me, Kite AI isn’t just a project. It’s an inspiration. Over the past three days, I poured my heart into creating a hand painted mural in doodle style, a piece that celebrates the spirit of Kite AI and the vision it represents. From mixing my own paints to priming the walls to sketching and coloring each line, every step was a dialogue between creativity and purpose. It wasn’t easy. Between the long hours and not feeling my best, I still kept going because I truly believe in what Kite AI stands for: a world where intelligence, identity, and innovation connect. This mural isn’t just art on a wall. It’s a story of dedication, belief, and the beauty of building something bigger than yourself. To everyone pushing boundaries in tech and creativity, this one’s for you. To KITE AI, thank you for inspiring me to turn vision into color. 🪁💫 What just happened in KITE AI lately? GoKiteAI just secured investment from Coinbase Ventures 🛡️, joining Paypal Ventures and General Catalyst in backing the future of autonomous AI payments. With Kite now natively integrated with the X402 Agent Payment Standard, AI agents can send, receive, and reconcile payments autonomously, the foundation of the coming agentic economy. I painted this mural to show what conviction looks like, and I’m proud to stand behind a project building the rails for the future. Who are the masterminds behind this great project? Get familiar with them! Project page KITE AI CEO Chi Zhang Co Founder Scott Shi - e/acc Project's CH page KITE AI 中文 Ecosystem and Community page Kite AI Community and Ecosystem Foundation page KITE Foundation Ecosystem product lead Henry Lee So many others can be found on thier page.

GM Crypto Trenches, Today, Art Meets Innovation: My 3-Day Journey with Kite AI 🎨🪁 They say art is how we express what words can’t, and for me, Kite AI isn’t just a project. It’s an inspiration. Over the past three days, I poured my heart into creating a hand painted mural in doodle style, a piece that celebrates the spirit of Kite AI and the vision it represents. From mixing my own paints to priming the walls to sketching and coloring each line, every step was a dialogue between creativity and purpose. It wasn’t easy. Between the long hours and not feeling my best, I still kept going because I truly believe in what Kite AI stands for: a world where intelligence, identity, and innovation connect. This mural isn’t just art on a wall. It’s a story of dedication, belief, and the beauty of building something bigger than yourself. To everyone pushing boundaries in tech and creativity, this one’s for you. To KITE AI, thank you for inspiring me to turn vision into color. 🪁💫 What just happened in KITE AI lately? GoKiteAI just secured investment from Coinbase Ventures 🛡️, joining Paypal Ventures and General Catalyst in backing the future of autonomous AI payments. With Kite now natively integrated with the X402 Agent Payment Standard, AI agents can send, receive, and reconcile payments autonomously, the foundation of the coming agentic economy. I painted this mural to show what conviction looks like, and I’m proud to stand behind a project building the rails for the future. Who are the masterminds behind this great project? Get familiar with them! Project page KITE AI CEO Chi Zhang Co Founder Scott Shi - e/acc Project's CH page KITE AI 中文 Ecosystem and Community page Kite AI Community and Ecosystem Foundation page KITE Foundation Ecosystem product lead Henry Lee So many others can be found on thier page.

TeaBagz

17,821 görüntüleme • 8 ay önce

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 görüntüleme • 17 gün önce