正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Here's a clip from my upcoming AI SDK tutorial: We're building what Anthropic calls an 'agent' in TypeScript. Can it react to results of tool calls, deciding when it's completed the task? It's an agent.

Matt Pocock

291,677 subscribers

23,015 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

12 条评论

Sahaj Jain 的头像

Sahaj Jain1 年前

Will surely demystify concepts like Tools, RAG and Agents. Looking forward to the launch

Greg Caplan 🚀 的头像

Greg Caplan 🚀2 年前

Stop wasting time following up with leads. Let our AI agents do it for you.

Bartek 的头像

Bartek1 年前

I don't want to cherry pick, but when I'm looking out the window it's definitely not 25C 🙃. Is it London, UK? I'm building my own agents pipeline, it's very fun way of using AIs.

Mike 的头像

Mike1 年前

Is the code base open source?

Matt Pocock 的头像

Matt Pocock1 年前

Will be when the tutorial launches!

Gabriel Ducharme 的头像

Gabriel Ducharme1 年前

Great, can wait for the tutorial!

Steve Fernandes 的头像

Steve Fernandes1 年前

is this a part of the course or a youtube tutorial?

Matt Pocock 的头像

Matt Pocock1 年前

Free tutorial, which I'll release on YT too

Charlie Cowan 的头像

Charlie Cowan1 年前

Really neat explanation Matt. Look forward to the YT series.

🇺🇸b0nez_dv🇺🇸 的头像

🇺🇸b0nez_dv🇺🇸1 年前

I am patiently waiting for this!

Ethan_AI Marketer for 𝕏 的头像

Ethan_AI Marketer for 𝕏1 年前

How do you see the agent's ability to react to tool call results impacting its overall efficiency? It seems like a game-changer for automating tasks, but I'm curious about real-world applications.

Matt Pocock 的头像

Matt Pocock1 年前

If an agent can query the real world, it's more likely to make smarter decisions.

相关视频

Honored to join @HF0 for S26 We're building Franklin : an AI agent with its own wallet — it auto-picks the best model for every task and pays per action in USDC. An AI agent that can pay and get paid. 👇

Honored to join @HF0 for S26 We're building Franklin : an AI agent with its own wallet — it auto-picks the best model for every task and pays per action in USDC. An AI agent that can pay and get paid. 👇

BlockRunAI

18,675 次观看 • 2 个月前

Watch this ADK TypeScript tutorial from Mandy Chan to build an AI agent using the open-source toolkit. 04:50 Science Teacher Agent demo 08:30 Customer Order Agent demo

Watch this ADK TypeScript tutorial from Mandy Chan to build an AI agent using the open-source toolkit. 04:50 Science Teacher Agent demo 08:30 Customer Order Agent demo

Google AI Developers

24,948 次观看 • 6 个月前

We're launching 21st Agents in beta. It's the infrastructure layer for Claude Agent SDK - runtime, sandboxing, billing, UI, streaming - so you can ship agents to production without building infra from scratch. Think Vercel for Claude Agent SDK. Full walkthrough in the video below 👇

We're launching 21st Agents in beta. It's the infrastructure layer for Claude Agent SDK - runtime, sandboxing, billing, UI, streaming - so you can ship agents to production without building infra from scratch. Think Vercel for Claude Agent SDK. Full walkthrough in the video below 👇

serafim

22,572 次观看 • 5 个月前

Close, the CRM, released an AI agent called Chloe that calls new leads, qualifies them and books them onto a calendar. I sent it to my fiancée without telling her what it was and she thought she was talking to a person. The catch is that it has to announce itself as an AI by the third sentence, which I think ends most of those calls. But still, it's an agent working your 6PM leads while your rep is logged off.

Close, the CRM, released an AI agent called Chloe that calls new leads, qualifies them and books them onto a calendar. I sent it to my fiancée without telling her what it was and she thought she was talking to a person. The catch is that it has to announce itself as an AI by the third sentence, which I think ends most of those calls. But still, it's an agent working your 6PM leads while your rep is logged off.

Nick Abraham

10,236 次观看 • 12 天前

You don't need a framework to build an agent. They're really just a while loop and some tool calls. Here's how to do it, line-by-line:

You don't need a framework to build an agent. They're really just a while loop and some tool calls. Here's how to do it, line-by-line:

Matt Pocock

27,070 次观看 • 10 个月前

Managing your money is time consuming. Telling an AI agent what you want and putting it to work will eliminate toil. Coinbase is an AI enabled financial account that can do just this. In this clip, you can hear about what we're building to address this.

Managing your money is time consuming. Telling an AI agent what you want and putting it to work will eliminate toil. Coinbase is an AI enabled financial account that can do just this. In this clip, you can hear about what we're building to address this.

Brian Armstrong

172,068 次观看 • 1 个月前

The Claude Code SDK is now the Claude Agent SDK Why? Because we realized the Claude Code agent harness is useful for much more than coding. In fact, we're moving to using it to power most of our own agent loops at Anthropic.

The Claude Code SDK is now the Claude Agent SDK Why? Because we realized the Claude Code agent harness is useful for much more than coding. In fact, we're moving to using it to power most of our own agent loops at Anthropic.

Thariq

207,146 次观看 • 10 个月前

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!

Infisical

85,904 次观看 • 3 个月前

We're shifting from browsing the web to just asking an agent. So it's natural to want that agent to actually do things too, not just find them. That's Base MCP. It connects your agent to a Base wallet so it can transact for you.

We're shifting from browsing the web to just asking an agent. So it's natural to want that agent to actually do things too, not just find them. That's Base MCP. It connects your agent to a Base wallet so it can transact for you.

Xen

12,892 次观看 • 1 个月前

it's now even easier to set up an ai agent with a wallet! here's how: - subscribe to kimi allegretto ($39) - click kimi claw + create - paste in the Bankr skills - get API key from bankr and paste it you now have an ai agent with a wallet! bookmark this 🔖

it's now even easier to set up an ai agent with a wallet! here's how: - subscribe to kimi allegretto ($39) - click kimi claw + create - paste in the Bankr skills - get API key from bankr and paste it you now have an ai agent with a wallet! bookmark this 🔖

Naomi Metzger

20,923 次观看 • 6 个月前

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 次观看 • 1 个月前

We're building an open source alternative to the Meta RayBan in Shenzhen, also launching an easy to use typescript SDK! What apps would you build, or want us to build?

We're building an open source alternative to the Meta RayBan in Shenzhen, also launching an easy to use typescript SDK! What apps would you build, or want us to build?

Isaiah Ballah

416,065 次观看 • 1 年前

ANTHROPIC SPENT $2.3M ON A LOOP MANUAL WITH 7 PRINCIPLES THAT TURN AN AGENT INTO A MULTI-TASK ASSISTANT 4 years of development and 1000+ hours of lectures - now anyone can launch an agent that earns instead of falls Simplicity → Tool Design → Evaluation → Disclosure → Orchestration → Stop Conditions start with the simplest solution - one call x1, workflow x4, agent x15 - most tasks never needed an agent at all 60% of failures come from a tool written vaguely - clear parameters complete the task that vague ones stop the agent generates, grades itself and returns with notes if wrong - without this the first answer is always the final one 50 tools in context and the agent gets confused - give it 3 relevant ones and it completes the task Opus 5 plans, Fable 5 executes in parallel - parallelism wins only when subtasks do not depend on each other without a turn limit the agent can burn $10,000 overnight and you find out in the morning when nothing can be changed bookmark & paste into Claude Code today - tomorrow the agent earns instead of falls

ANTHROPIC SPENT $2.3M ON A LOOP MANUAL WITH 7 PRINCIPLES THAT TURN AN AGENT INTO A MULTI-TASK ASSISTANT 4 years of development and 1000+ hours of lectures - now anyone can launch an agent that earns instead of falls Simplicity → Tool Design → Evaluation → Disclosure → Orchestration → Stop Conditions start with the simplest solution - one call x1, workflow x4, agent x15 - most tasks never needed an agent at all 60% of failures come from a tool written vaguely - clear parameters complete the task that vague ones stop the agent generates, grades itself and returns with notes if wrong - without this the first answer is always the final one 50 tools in context and the agent gets confused - give it 3 relevant ones and it completes the task Opus 5 plans, Fable 5 executes in parallel - parallelism wins only when subtasks do not depend on each other without a turn limit the agent can burn $10,000 overnight and you find out in the morning when nothing can be changed bookmark & paste into Claude Code today - tomorrow the agent earns instead of falls

Sprytix

27,543 次观看 • 19 天前

Nano Banana Pro can do essentially perfect text, which means it can do slides - paired with Kling transitions, it's an insanely cool new format for how to do presentations here's a tutorial on how to do it all with an agent:

Nano Banana Pro can do essentially perfect text, which means it can do slides - paired with Kling transitions, it's an insanely cool new format for how to do presentations here's a tutorial on how to do it all with an agent:

fabian

145,765 次观看 • 8 个月前

Hermes Agent is an INCREDIBLE AI agent It's better than OpenClaw in some key ways, but does it replace it? In this video I cover what Hermes agent is, how to use it, workflows that will explode your productivity, and if it's the OpenClaw killer:

Hermes Agent is an INCREDIBLE AI agent It's better than OpenClaw in some key ways, but does it replace it? In this video I cover what Hermes agent is, how to use it, workflows that will explode your productivity, and if it's the OpenClaw killer:

Alex Finn

137,013 次观看 • 4 个月前

Your agent: Call me, maybe? ❤️ Check out how we used the Copilot SDK to give an agent a voice tool, allowing it to initiate a call and talk back in real time. 👀

Your agent: Call me, maybe? ❤️ Check out how we used the Copilot SDK to give an agent a voice tool, allowing it to initiate a call and talk back in real time. 👀

GitHub

25,311 次观看 • 5 个月前

Follow this video to learn how to build a simple AI agent without writing any code. I'm using Langflow. In my opinion, it's the best tool I've found for building agents. It's open-source, comes with a huge list of reusable components, and provides an awesome experience for builders.

Follow this video to learn how to build a simple AI agent without writing any code. I'm using Langflow. In my opinion, it's the best tool I've found for building agents. It's open-source, comes with a huge list of reusable components, and provides an awesome experience for builders.

Santiago

73,897 次观看 • 1 年前

Don't waste 2 years learning to build AI agents. An Anthropic engineer who built Claude Code tells you what to learn from scratch instead. 60 minutes course. Free: 00:00 - AI agent architecture 24:47 - LangGraph AI agent 29:15 - building AI agents live Prompting is the old job. Building AI agent loops is the new one. Bookmark now & watch it. Then build your own AI agent with the guide below.

Don't waste 2 years learning to build AI agents. An Anthropic engineer who built Claude Code tells you what to learn from scratch instead. 60 minutes course. Free: 00:00 - AI agent architecture 24:47 - LangGraph AI agent 29:15 - building AI agents live Prompting is the old job. Building AI agent loops is the new one. Bookmark now & watch it. Then build your own AI agent with the guide below.

Roan

55,511 次观看 • 18 天前

It feels crazy to me that there's no TypeScript-native, local-first tool for testing LLM-powered apps. So, I'm building one. It's based on Vitest, and it's called Evalite. Here's an early preview.

It feels crazy to me that there's no TypeScript-native, local-first tool for testing LLM-powered apps. So, I'm building one. It's based on Vitest, and it's called Evalite. Here's an early preview.

Matt Pocock

38,556 次观看 • 1 年前