正在加载视频...

视频加载失败

返回首页

At today’s Amazon Web Services Summit NYC, we unveiled a new Bedrock capability called AgentCore – a set of powerful building blocks that will change how you can deploy agents into production in a secure, scalable, and flexible way.

ajassy's profile picture

Andy Jassy

3,927,299 subscribers

230,965 次观看 • 1 年前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

11 条评论

britton winterrose 的头像
britton winterrose1 年前

@awscloud Andy I can’t imagine the burden you bear but please take care of yourself.

bshaan 的头像
bshaan1 年前

Agent Core: 1. secure serverless runtime (each agent run's on its own VM) 2. memory (short and log term) to personalize agents 3. identity (auth and access) 4. api/lambda -> mcp (give tools to agents) 5. code and browser tool (execute complex code and navigate the web) 6. observability (monitor agents)

Vittorio 的头像
Vittorio1 年前

@awscloud u rock

Mobile Scanner 的头像
Mobile Scanner1 年前

Scan any documents, convert images into text, PDF files, etc. 👍

Reno Seros ` 的头像
Reno Seros `1 年前

@awscloud ✨

Alex Volkov (Thursd/AI) 的头像
Alex Volkov (Thursd/AI)1 年前

@awscloud where's Alexa+? How can I get it in my home?

Lon 的头像
Lon1 年前

@awscloud giddy up

Dallas Klein 的头像
Dallas Klein1 年前

@awscloud Thanks Andy! Hoping I can hand off some docs to Kiro and come back and have an agent spun up

Carlos Carpio 的头像
Carlos Carpio1 年前

@awscloud Wow, you guys are getting serious! 💪❤️

Simon Leyland 的头像
Simon Leyland1 年前

@awscloud AWS will be able to house hundreds of millions of virtual workforce. Will transform industry and society for the better.

Quizical 的头像
Quizical1 年前

@awscloud Why are Amazon orders taking so long to ship now? Amazon is getting worse and worse by the day. Maybe someone should be looking into it, and fixing the problem, instead of looking for new ways to make more money for Amazon. Think of your customers for once.

相关视频

🚀 Here’s more on AgentCore, launched today: If AI agents are going to transform how we work and live, developers need the right set of tools to move them from prototype to production at scale. Today, I'm thrilled to announce Amazon Bedrock AgentCore, a comprehensive set of services to deploy and operate highly capable agents securely at scale. The journey from prototype to production for AI agents has been filled with complex infrastructure challenges. Teams spend months building secure runtime environments, implementing memory systems, and creating monitoring solutions. AgentCore eliminates this undifferentiated heavy lifting, with fully-managed, modular services - providing everything you need to operate trustworthy agents. What makes AgentCore powerful: 🟠 Complete Development Flexibility: Build agents your way using any framework and any model, and work with any protocol (including MCP and A2A) - all while maintaining enterprise-grade security and control 🟠 Purpose-Built Infrastructure: First serverless runtime to offer framework-agnostic flexibility, complete session isolation, and industry-leading 8-hour workload support 🟠 Trust and Reliability: Built on AWS's proven security foundation with built-in identity controls and strict security boundaries for operating agents at scale 🟠 Composable Services: Use exactly what you need independently or together, paying only for what you use as your needs evolve AgentCore represents a significant milestone in our mission to make advanced AI accessible and practical for every organization. Whether you're just starting with AI agents or scaling enterprise-wide implementations, AgentCore gives you the foundation to build with confidence. This is just the beginning of our journey to enable an agentic future. Can't wait to see the transformative solutions you'll build with AgentCore! Bring your AI agents to life at scale – learn more about AgentCore today. Amazon Web Services #AmazonBedrock #AgentCore
1:29

🚀 Here’s more on AgentCore, launched today: If AI agents are going to transform how we work and live, developers need the right set of tools to move them from prototype to production at scale. Today, I'm thrilled to announce Amazon Bedrock AgentCore, a comprehensive set of services to deploy and operate highly capable agents securely at scale. The journey from prototype to production for AI agents has been filled with complex infrastructure challenges. Teams spend months building secure runtime environments, implementing memory systems, and creating monitoring solutions. AgentCore eliminates this undifferentiated heavy lifting, with fully-managed, modular services - providing everything you need to operate trustworthy agents. What makes AgentCore powerful: 🟠 Complete Development Flexibility: Build agents your way using any framework and any model, and work with any protocol (including MCP and A2A) - all while maintaining enterprise-grade security and control 🟠 Purpose-Built Infrastructure: First serverless runtime to offer framework-agnostic flexibility, complete session isolation, and industry-leading 8-hour workload support 🟠 Trust and Reliability: Built on AWS's proven security foundation with built-in identity controls and strict security boundaries for operating agents at scale 🟠 Composable Services: Use exactly what you need independently or together, paying only for what you use as your needs evolve AgentCore represents a significant milestone in our mission to make advanced AI accessible and practical for every organization. Whether you're just starting with AI agents or scaling enterprise-wide implementations, AgentCore gives you the foundation to build with confidence. This is just the beginning of our journey to enable an agentic future. Can't wait to see the transformative solutions you'll build with AgentCore! Bring your AI agents to life at scale – learn more about AgentCore today. Amazon Web Services #AmazonBedrock #AgentCore

Swami Sivasubramanian

11,646 次观看 • 1 年前

🚀 Today we're announcing the first managed end-to-end payment capabilities for autonomous agents in preview in Amazon Bedrock AgentCore. Built with Coinbase and Stripe, so developers can focus on what their agents do, not on how they pay. The agentic economy is just getting started. Here's a first look at AgentCore payments ➡️
2:59

🚀 Today we're announcing the first managed end-to-end payment capabilities for autonomous agents in preview in Amazon Bedrock AgentCore. Built with Coinbase and Stripe, so developers can focus on what their agents do, not on how they pay. The agentic economy is just getting started. Here's a first look at AgentCore payments ➡️

Swami Sivasubramanian

33,956 次观看 • 2 个月前

At Amazon Web Services re:Invent, our SVP of Devices & Services, Panos Panay, put his skills to the test in a game of "This or That" — trying to spot the difference between real photos and AI-generated images created by Amazon Nova. Spoiler: It's harder than you think! We've unveiled major AI innovations at re:Invent that are transforming how we create, work, and imagine. Amazon Nova's image generation capabilities showcase just how far generative AI has come. See if you can spot the difference.
0:35

At Amazon Web Services re:Invent, our SVP of Devices & Services, Panos Panay, put his skills to the test in a game of "This or That" — trying to spot the difference between real photos and AI-generated images created by Amazon Nova. Spoiler: It's harder than you think! We've unveiled major AI innovations at re:Invent that are transforming how we create, work, and imagine. Amazon Nova's image generation capabilities showcase just how far generative AI has come. See if you can spot the difference.

Amazon

58,206 次观看 • 8 个月前

"How can we start to assemble these building blocks into a new app that creates the onchain economy for a billion people?" - Brian Armstrong
1:30

"How can we start to assemble these building blocks into a new app that creates the onchain economy for a billion people?" - Brian Armstrong

Base

110,617 次观看 • 1 年前

What we’re building for you and your agents: • Deploy with Projects: programmatically provision services from the CLI—now available to everyone. • Sell with Machine Payments Protocol: a protocol that lets agents know how to pay for services. • Buy with Link agent wallet: enable agents to spend on your behalf. Everything we announced at Stripe Sessions:
1:18

What we’re building for you and your agents: • Deploy with Projects: programmatically provision services from the CLI—now available to everyone. • Sell with Machine Payments Protocol: a protocol that lets agents know how to pay for services. • Buy with Link agent wallet: enable agents to spend on your behalf. Everything we announced at Stripe Sessions:

Stripe

31,424 次观看 • 3 个月前

New short course on Serverless LLM apps with Amazon Bedrock, taught by Amazon Web Services' Mike G Chambers! A serverless architecture enables you to quickly deploy your applications without needing to set up and manage compute servers to run your applications on, the maintenance of which can be another full-time job. In this course, you’ll learn how to do this by using an event-driven architecture to build complex AI workflows. Mike illustrate these concepts by building a cool application that automatically detects incoming customer inquiries, transcribes them with ASR (automatic speech recognition), summarizes them with an LLM using Bedrock, and deploys serverless with AWS Lambda. I hope this course makes it much easier for you to build and deploy LLM applications requiring multi-step AI workflows. Please sign up here:
3:10

New short course on Serverless LLM apps with Amazon Bedrock, taught by Amazon Web Services' Mike G Chambers! A serverless architecture enables you to quickly deploy your applications without needing to set up and manage compute servers to run your applications on, the maintenance of which can be another full-time job. In this course, you’ll learn how to do this by using an event-driven architecture to build complex AI workflows. Mike illustrate these concepts by building a cool application that automatically detects incoming customer inquiries, transcribes them with ASR (automatic speech recognition), summarizes them with an LLM using Bedrock, and deploys serverless with AWS Lambda. I hope this course makes it much easier for you to build and deploy LLM applications requiring multi-step AI workflows. Please sign up here:

Andrew Ng

108,171 次观看 • 2 年前

👀 Modern Skies Are Coming… Stay tuned to U.S. Department of Transportation all day long as we host a special summit on a NEW era of FLYING and how it will change the way YOU travel ✈️
1:04

👀 Modern Skies Are Coming… Stay tuned to U.S. Department of Transportation all day long as we host a special summit on a NEW era of FLYING and how it will change the way YOU travel ✈️

Secretary Sean Duffy

44,023 次观看 • 3 个月前

Wild! With the new mention capability for GPTs, I can create an app with Grimoire, and seamlessly ask DesignerGPT to deploy it. No change in instructions needed – it's pure intelligence at work. ✨ You can deploy all your ideas for free, with just a mention of @ DesignerGPT.
0:33

Wild! With the new mention capability for GPTs, I can create an app with Grimoire, and seamlessly ask DesignerGPT to deploy it. No change in instructions needed – it's pure intelligence at work. ✨ You can deploy all your ideas for free, with just a mention of @ DesignerGPT.

Pietro Schirano

149,559 次观看 • 2 年前

We're building heavily & being busy. A lot of new features rolling out soon. One of the most anticipated: Intelligence Agents you can deploy to the web — vulnerability scanning, monitoring, and surveillance of essentially anything that matters. This is one branch of the privacy layer AI at the core of Serus. Stay tuned.
1:22

We're building heavily & being busy. A lot of new features rolling out soon. One of the most anticipated: Intelligence Agents you can deploy to the web — vulnerability scanning, monitoring, and surveillance of essentially anything that matters. This is one branch of the privacy layer AI at the core of Serus. Stay tuned.

Serus

50,410 次观看 • 3 个月前

Tammy Camp, founder of Stronghold, highlighted how Ripple and Stellar can be seamlessly embedded into applications during a panel hosted by Amazon Web Services.🙇‍♂️ Listen closely.👇
0:42

Tammy Camp, founder of Stronghold, highlighted how Ripple and Stellar can be seamlessly embedded into applications during a panel hosted by Amazon Web Services.🙇‍♂️ Listen closely.👇

SMQKE

138,533 次观看 • 1 年前

NEW - Anthropic's CEO: "We're increasingly close to what I've called a country of geniuses in a data center—a set of AI agents that are more capable than most humans and most things and can coordinate at superhuman speed."
0:36

NEW - Anthropic's CEO: "We're increasingly close to what I've called a country of geniuses in a data center—a set of AI agents that are more capable than most humans and most things and can coordinate at superhuman speed."

Disclose.tv

140,324 次观看 • 5 个月前

Just SKETCH IT, and GROK will bring it into reality for you! Building a web page has never been easier! See below how you can build a web page from a drawing using Grok! 👇
1:07

Just SKETCH IT, and GROK will bring it into reality for you! Building a web page has never been easier! See below how you can build a web page from a drawing using Grok! 👇

Nima Owji

1,445,790 次观看 • 1 年前

⚠️AMAZON WEB SERVICES & RIPPLE discussing AMAZON Bedrock for the XRPL🔥 The overview of this video: XRPL runs on high-performance C++ code (A powerful programming language) . At scale, C++ systems produce large volumes of cryptic logs (history). AWS partners with Ripple, using AMAZON Bedrock (a platform that hosts artificial intelligence agents) to help source the right logs and to understand systems behaviour, reducing time constraints from approximately 2 to 3 days, down to 2 to 3 minutes🔥. Thus reducing the burden on Ripple engineers🔥 This will enable seamless deployment when the new system is eventually implemented. NFA, DYOR⚠️ #XRPLedger
14:21

⚠️AMAZON WEB SERVICES & RIPPLE discussing AMAZON Bedrock for the XRPL🔥 The overview of this video: XRPL runs on high-performance C++ code (A powerful programming language) . At scale, C++ systems produce large volumes of cryptic logs (history). AWS partners with Ripple, using AMAZON Bedrock (a platform that hosts artificial intelligence agents) to help source the right logs and to understand systems behaviour, reducing time constraints from approximately 2 to 3 days, down to 2 to 3 minutes🔥. Thus reducing the burden on Ripple engineers🔥 This will enable seamless deployment when the new system is eventually implemented. NFA, DYOR⚠️ #XRPLedger

ProfessoRipplEffect

93,327 次观看 • 6 个月前

LIVE NOW -- x402 & The Agentic Internet | Lincoln Murr In our twelfth talk of the Bankless Summit, Coinbase 🛡️ product lead lincoln.base.eth explains how x402 revives the long-dormant internet payment standard and why the rise of AI agents makes it newly essential. He outlines how agents will consume and pay for services across the web, why internet native payments need stablecoin rails, and how x402 can unlock agentic commerce at global scale by giving both humans and bots a simple, universal way to send value online. ----- [Bankless Summit in partnership with M0]
19:03

LIVE NOW -- x402 & The Agentic Internet | Lincoln Murr In our twelfth talk of the Bankless Summit, Coinbase 🛡️ product lead lincoln.base.eth explains how x402 revives the long-dormant internet payment standard and why the rise of AI agents makes it newly essential. He outlines how agents will consume and pay for services across the web, why internet native payments need stablecoin rails, and how x402 can unlock agentic commerce at global scale by giving both humans and bots a simple, universal way to send value online. ----- [Bankless Summit in partnership with M0]

Bankless

31,394 次观看 • 8 个月前

OpenAI launched Agents in ChatGPT today. It’s great for consumers who want to automate tasks in ChatGPT. But what if you want to build features powered by the same tools? I dropped put same demo prompt into Director, our web agent builder, to generate a script for that. Director enables anyone to build software powered by web agents. You prompt it once, and get a deterministic web agent that you can integrate into your application. It's a great starting point for building powerful buttons that do work FOR your users.
1:05

OpenAI launched Agents in ChatGPT today. It’s great for consumers who want to automate tasks in ChatGPT. But what if you want to build features powered by the same tools? I dropped put same demo prompt into Director, our web agent builder, to generate a script for that. Director enables anyone to build software powered by web agents. You prompt it once, and get a deterministic web agent that you can integrate into your application. It's a great starting point for building powerful buttons that do work FOR your users.

Paul Klein IV

32,299 次观看 • 1 年前

Skip the setup slog. With Google AI Studio, you can launch in minutes and spend your time where it matters: creating. Jump right into building your project: ⚙️Generate a backend instantly with one click 💻Deploy your app server in under 5 minutes ☁️Post a shareable, scalable web app directly to GoogleCloud
0:29

Skip the setup slog. With Google AI Studio, you can launch in minutes and spend your time where it matters: creating. Jump right into building your project: ⚙️Generate a backend instantly with one click 💻Deploy your app server in under 5 minutes ☁️Post a shareable, scalable web app directly to GoogleCloud

Google for Startups

11,151 次观看 • 11 个月前

The calendar can change, we can go into a new year, but if our thinking is the same, nothing will be different. Why don’t you change your mind? Break out of those ruts that have held you back. Tune into Joel’s message today, "A New Mindset"!
0:33

The calendar can change, we can go into a new year, but if our thinking is the same, nothing will be different. Why don’t you change your mind? Break out of those ruts that have held you back. Tune into Joel’s message today, "A New Mindset"!

Joel Osteen

78,011 次观看 • 2 年前

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:
2:06

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

Andrew Ng

186,133 次观看 • 1 年前