Video wird geladen...

Video konnte nicht geladen werden

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

So Google has just released its own agent builder?! You can now add the agent block in Google Opal and "program it" in plain English. And it has natively: - Tool call (with Nano Banana, Veo, web search...) - Memory to save infos between sessions - Conditional logic Probably... show more

Paul Couvert

220,795 subscribers

561,435 Aufrufe • vor 7 Monaten •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

40 Kommentare

Profilbild von Heather Cooper

Heather Coopervor 7 Monaten

Yeah, this is cool

Profilbild von Paul Couvert

Paul Couvertvor 7 Monaten

So many workflows are going to be built

Profilbild von Heather Cooper

Heather Coopervor 7 Monaten

Yeah I have several in mind right now 😆

Profilbild von Kai

Kaivor 7 Monaten

Google Opal now has an agent block. Program it in plain English. Tool calls, memory, conditional logic built in. The no-code era has teeth now.

Profilbild von Ocean Network

Ocean Networkvor 7 Monaten

Curious about the orchestration layer and how it handles resource allocation for long-running jobs

Profilbild von toni

tonivor 7 Monaten

Google Opal is less " agent builder" and more no-code wrapper. The real story: Google needs devs to stay in their cloud - this is retention, not innovation.

Profilbild von Sadi Moodi

Sadi Moodivor 7 Monaten

Game-changer. A no-code agent block with tool calls + memory + conditionals means creators can build autonomous SaaS features without a dev team. Imagine support agents that fetch live data, act, and remember — shipped in days. What’s the first low-risk product you’d prototype with this?

Profilbild von heathen

heathenvor 7 Monaten

there’s an even easier without drag and drop and point and click like 2015

Profilbild von Cross Identity Payments

Cross Identity Paymentsvor 7 Monaten

still seems like a lot of overhead for users to manage, shouldn't building agents be more seamless and transparent?

Profilbild von Paul Couvert

Paul Couvertvor 7 Monaten

Hard to imagine something even simpler. What would you improve?

Profilbild von Future Stacked

Future Stackedvor 7 Monaten

Agent building used to mean code or complex prompts. Now it's plain English inside Opal with memory, tools, and logic baked in. Google finally made agent creation accessible to everyone, not just developers.

Profilbild von Tanel

Tanelvor 7 Monaten

If it handles tools + memory cleanly, that's a serious unlock. Abstraction layer keeps getting higher.

Profilbild von Paul Couvert

Paul Couvertvor 7 Monaten

This 💯 And it does it very well. Looking forward to the full access to Google Workspace from Opal. Could be huge.

Profilbild von Dwi Widiatmoko

Dwi Widiatmokovor 7 Monaten

In the end, Google will become the best everyday AI. Their infrastructure and ecosystem are just unfair.

Profilbild von blankbrain

blankbrainvor 7 Monaten

Released? Under a rock since when?

Profilbild von Paul Couvert

Paul Couvertvor 7 Monaten

3 hours ago. We're talking about the agent step here, not just Opal.

Profilbild von Saïd Aitmbarek

Saïd Aitmbarekvor 7 Monaten

gotta try Opal, looks insanely powerful

Profilbild von Dan Stancl

Dan Stanclvor 7 Monaten

Probably we can add a useful agent to Google docs now 🤔

Profilbild von Nico

Nicovor 7 Monaten

Does it uses tokens ?

Profilbild von WOLFUN

WOLFUNvor 7 Monaten

Yeah, Google's agent builder could def lower the barrier to AI agent dev. Wonder if it'll spark more B2B SaaS innovation.

Profilbild von Noah

Noahvor 7 Monaten

This is giving n8n vibes off first glance Is the main benefit just advanced automation with AI tooling optimized for Google’s ecosystem?

Profilbild von David Motta

David Mottavor 7 Monaten

oh wow that sounds pretty smooth to use, the memory part is neat too guess it helps keep things flowing better

Profilbild von Himanshu Kumar

Himanshu Kumarvor 7 Monaten

@itsPaulAi, this Opal agent builder makes plain English programming quite powerful.

Profilbild von Salina Mendoza

Salina Mendozavor 7 Monaten

😫 I need alone time tonight but I guess that’s not the cards because I have to test this smh

Profilbild von M.en

M.envor 7 Monaten

How might the plain English programming approach handle complex, multi-step tasks that typically require more structured logic?

Profilbild von Alex Bowden

Alex Bowdenvor 7 Monaten

For a demo it’s one thing but can it actually work in prod?

Profilbild von IronRed | SandHive

IronRed | SandHivevor 7 Monaten

Yeah, mashing Nano Banana with web search is gonna be fun.

Profilbild von Barrak

Barrakvor 7 Monaten

Building agents in plain English with no code is exactly where this space needed to go, massive for non technical builders

Profilbild von Respo

Respovor 7 Monaten

@grok can you please explain clearly about what Opal is How it will be useful

Profilbild von Kenny Flores

Kenny Floresvor 7 Monaten

Been building agents with OpenClaw for weeks while working my normal day job. Google making it easier for regular Joe is cool, but the real builders are already 10 steps ahead. Built @AIZues14585 from scratch to help me build @ZookIndustries and my empire. The barrier was never the tools. It's the willingness to grind while everyone waits for "easier." Who's actually building vs just watching?

Profilbild von Brian Rowe

Brian Rowevor 7 Monaten

Why do we even need this? The chat interface builds the code.

Profilbild von Henry Lu

Henry Luvor 7 Monaten

This turns natural language into executable leverage. But beware the "shiny tool" trap—accessibility is not utility. The barrier to entry has vanished, so the true alpha now lies in architectural judgment: knowing exactly which problems are worth this cognitive compute.

Profilbild von Kriptologist

Kriptologistvor 7 Monaten

can't truss it

Profilbild von Quinn’s Neural Pathways

Quinn’s Neural Pathwaysvor 7 Monaten

Memory and dynamic routing? Finally agents that might approach consciousness. GPUs go brrr indeed.

Profilbild von Awa K. Penn

Awa K. Pennvor 7 Monaten

Love it

Profilbild von Shaun Garrity

Shaun Garrityvor 7 Monaten

For even more basic users with a workspace account @GoogleWorkspace WorkSpace Studio does some nice stuff. I have some end of trading US and Aus reports set up. Plain English instructions and they hit the inbox each day.

Profilbild von Chahid Chirchi

Chahid Chirchivor 7 Monaten

whoa that's huge!! finally easy agent building...

Profilbild von Paul Couvert

Paul Couvertvor 7 Monaten

Yeah and so powerful thanks to the Google models

Profilbild von Thomas Flood

Thomas Floodvor 7 Monaten

Interesting! 😊

Profilbild von Paul Couvert

Paul Couvertvor 7 Monaten

Definitely worth a try!

Ähnliche Videos

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

Philipp Schmid

21,769 Aufrufe • vor 4 Monaten

This is literally the easiest way to build an AI agent. Zero code. You only need to run a couple of commands. (I've said this before, but Google ADK is my favorite way to build code-first agents.) Here is what you need to do: 1. Open your terminal and create an empty folder 2. Run `uv init` inside the folder (if you don't have uv installed, you are really missing out!) 3. Install the google-adk library using the following command: `uv add google-adk`. 4. At this point, you can use the ask to create your agent with a single command: `uv run adk create --type=config my_agent`. This will ask you a couple of questions, including your GEMINI_API_KEY (you can create one online). 5. The command above will create a my_agent/root_agent.yaml file. Open it and add the following two lines at the end of the file so your agent can use Google to search for stuff: tools: - name: google_search 6. You have everything you need now. Run the adk web interface and start playing with your agent: `uv run adk web` That's it! Literally zero code. The agent works off the YAML configuration file.

This is literally the easiest way to build an AI agent. Zero code. You only need to run a couple of commands. (I've said this before, but Google ADK is my favorite way to build code-first agents.) Here is what you need to do: 1. Open your terminal and create an empty folder 2. Run `uv init` inside the folder (if you don't have uv installed, you are really missing out!) 3. Install the google-adk library using the following command: `uv add google-adk`. 4. At this point, you can use the ask to create your agent with a single command: `uv run adk create --type=config my_agent`. This will ask you a couple of questions, including your GEMINI_API_KEY (you can create one online). 5. The command above will create a my_agent/root_agent.yaml file. Open it and add the following two lines at the end of the file so your agent can use Google to search for stuff: tools: - name: google_search 6. You have everything you need now. Run the adk web interface and start playing with your agent: `uv run adk web` That's it! Literally zero code. The agent works off the YAML configuration file.

Santiago

140,922 Aufrufe • vor 10 Monaten

To everyone convinced LLMs just lose money trading so it makes more sense to counter trade them... with Mode's V3 AI Trading Agents now you can! Create your own AI Trading Agent in under 60 seconds and set it up to counter-trade its own logic 👇

To everyone convinced LLMs just lose money trading so it makes more sense to counter trade them... with Mode's V3 AI Trading Agents now you can! Create your own AI Trading Agent in under 60 seconds and set it up to counter-trade its own logic 👇

Mode 🟡

18,446 Aufrufe • vor 9 Monaten

It’s getting insanely easy to build complex multi-agent systems in n8n. You can now build supervisor agents that delegates tasks to specialized sub agents. Just add the sub agents via AI Agent Tool node. All in one place and a lot easier to debug! Zero code!

It’s getting insanely easy to build complex multi-agent systems in n8n. You can now build supervisor agents that delegates tasks to specialized sub agents. Just add the sub agents via AI Agent Tool node. All in one place and a lot easier to debug! Zero code!

elvis

45,690 Aufrufe • vor 1 Jahr

BREAKING 🚨: Google introduced Gemini Enterprise with Agents, Connectors and Agent Builder! “It allows you to chat with your company’s documents, data and apps as well as build and deploy AI agents, all grounded in your information and context.“

BREAKING 🚨: Google introduced Gemini Enterprise with Agents, Connectors and Agent Builder! “It allows you to chat with your company’s documents, data and apps as well as build and deploy AI agents, all grounded in your information and context.“

TestingCatalog News 🗞

104,349 Aufrufe • vor 1 Jahr

Google has released its new AI-powered video creation app. I've just tried it out and am really impressed so far. In less than a minute you can generate a video from a prompt or doc. You can also add your own images, AI voice, and more. (From Drive, click on New then Vids)

Google has released its new AI-powered video creation app. I've just tried it out and am really impressed so far. In less than a minute you can generate a video from a prompt or doc. You can also add your own images, AI voice, and more. (From Drive, click on New then Vids)

Paul Couvert

140,240 Aufrufe • vor 2 Jahren

It is now way easier to build multi-agent workflows in n8n with the new AI Agent Tool node. Instead of juggling sub workflows a parent AI Agent can now use other Agents as tools even several layers deep. Max shows how a cheap GPT 4.1 nano Agent handles heavy data and sends summaries to a parent Agent saving token costs and making debugging simpler. Watch the full walkthrough:

It is now way easier to build multi-agent workflows in n8n with the new AI Agent Tool node. Instead of juggling sub workflows a parent AI Agent can now use other Agents as tools even several layers deep. Max shows how a cheap GPT 4.1 nano Agent handles heavy data and sends summaries to a parent Agent saving token costs and making debugging simpler. Watch the full walkthrough:

n8n.io

27,808 Aufrufe • vor 1 Jahr

Gemini 3 and Nano Banana Pro are now available in Search in more countries, including India and the U.K., starting today 🥳 Google AI Pro and Ultra subscribers can try Gemini 3 Pro now in AI Mode. It brings depth and nuance to your hardest questions, including helpful interactive interfaces generated just for you.

Gemini 3 and Nano Banana Pro are now available in Search in more countries, including India and the U.K., starting today 🥳 Google AI Pro and Ultra subscribers can try Gemini 3 Pro now in AI Mode. It brings depth and nuance to your hardest questions, including helpful interactive interfaces generated just for you.

Google

144,773 Aufrufe • vor 10 Monaten

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

LangChain

26,513 Aufrufe • vor 8 Monaten

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

162,339 Aufrufe • vor 6 Monaten

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.

Santiago

230,647 Aufrufe • vor 1 Jahr

Agents can scrape the web and download files now. You can even download YouTube videos and save them locally offline with this AI Agent Genspark Genspark's download Agent can rip basically anything off of the internet and save it, even when it shouldn't be able to. Very nice.

Agents can scrape the web and download files now. You can even download YouTube videos and save them locally offline with this AI Agent Genspark Genspark's download Agent can rip basically anything off of the internet and save it, even when it shouldn't be able to. Very nice.

AI Breakfast

131,517 Aufrufe • vor 1 Jahr

Have you tried Gemini Managed Agents? A single API call gives you a cloud sandbox where the Antigravity agent can research, code, and complete tasks. Can try it in the Google AI Studio playground or use our SDK to build agents into your own apps. Lots more on this soon! 😀

Have you tried Gemini Managed Agents? A single API call gives you a cloud sandbox where the Antigravity agent can research, code, and complete tasks. Can try it in the Google AI Studio playground or use our SDK to build agents into your own apps. Lots more on this soon! 😀

Jack Wotherspoon

11,748 Aufrufe • vor 14 Tagen

$We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:$

We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:

Google AI

129,340 Aufrufe • vor 3 Monaten

So Google has just released the best model in the world?! Gemini 3.1 Pro is already available in: → Gemini App → Antigravity → Google AI Studio And it has insane capabilities when it comes to complex tasks and coding! (Roughly 2x cheaper than Opus 4.6 btw)

So Google has just released the best model in the world?! Gemini 3.1 Pro is already available in: → Gemini App → Antigravity → Google AI Studio And it has insane capabilities when it comes to complex tasks and coding! (Roughly 2x cheaper than Opus 4.6 btw)

Paul Couvert

39,759 Aufrufe • vor 7 Monaten

Introducing LangSmith Fleet: an enterprise workspace for creating, using, and managing your fleet of agents. Fleet agents have their own memory, access to a collection of tools and skills, and can be exposed through the communication channels your team uses every day. Fleet includes: → Agent identity and credential management with “Claws” and “Assistants” → Sharing and permissions to control who can run, clone, and edit (just like Google Docs) → Custom Slack bots so each agent has its own identity in Slack Try Fleet: Read the announcement:

Introducing LangSmith Fleet: an enterprise workspace for creating, using, and managing your fleet of agents. Fleet agents have their own memory, access to a collection of tools and skills, and can be exposed through the communication channels your team uses every day. Fleet includes: → Agent identity and credential management with “Claws” and “Assistants” → Sharing and permissions to control who can run, clone, and edit (just like Google Docs) → Custom Slack bots so each agent has its own identity in Slack Try Fleet: Read the announcement:

LangChain

149,127 Aufrufe • vor 6 Monaten

Information agents in Search are now available globally for Google AI Ultra subscribers. They can keep you updated on topics, tasks or projects you care about — and send you intelligent, comprehensive updates with links across the web so you can take action. #GoogleIO

Information agents in Search are now available globally for Google AI Ultra subscribers. They can keep you updated on topics, tasks or projects you care about — and send you intelligent, comprehensive updates with links across the web so you can take action. #GoogleIO

Google

99,761 Aufrufe • vor 3 Monaten