Loading video...

Video Failed to Load

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

Alright, now that we know what an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are... show more

Google AI

2,396,146 subscribers

22,487 views • 10 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!

swarms

32,440 views • 1 year ago

Excited to introduce Orbit - a new API specifically built for coding agents to discover, evaluate, and integrate public APIs. Orbit has two simple tools: search and integrate. All your agent needs to do is describe the task, and Orbit will generate a task brief to integrate the API. Best of all: it is completely free! No auth, no set up. Just add it to Claude, Cursor, OpenCode @devindesktop or any other coding agent. Check it out here:

Excited to introduce Orbit - a new API specifically built for coding agents to discover, evaluate, and integrate public APIs. Orbit has two simple tools: search and integrate. All your agent needs to do is describe the task, and Orbit will generate a task brief to integrate the API. Best of all: it is completely free! No auth, no set up. Just add it to Claude, Cursor, OpenCode @devindesktop or any other coding agent. Check it out here:

Abhinav Asthana

481,810 views • 1 month ago

Rewarding real product usage just got a little more interesting. NeoSoul is now LIVE on ActionFi. Your task? Create your first AI agent on NeoSoul. Complete the task. Meet the success criteria. Get rewarded. You've got 2 weeks. Head to Action Model, open the ActionFi tab, and go take action.

Rewarding real product usage just got a little more interesting. NeoSoul is now LIVE on ActionFi. Your task? Create your first AI agent on NeoSoul. Complete the task. Meet the success criteria. Get rewarded. You've got 2 weeks. Head to Action Model, open the ActionFi tab, and go take action.

Action Model

33,987 views • 1 month ago

holy sh*t. Jev's founder Diogo Almeida dropped a Google Doc on coding agents one of these PDFs has the map everyone needs: where Jev sits in an agent loop ↓ agents do the work, Jev makes the calls, the LLM only writes: 1 → task in: one Noul before anything runs. in scope, or does a human need to see it first? 2 → dispatch: a Choice picks who takes the step (research, write or review). act at 0.85+, everything below goes to review 3 → act: Jev gates the tool call (allow, confirm or block). the LLM only writes the arguments 4 → check: a Score decides what comes back (drop, summary or keep). whatever Jev is unsure of goes to a human 5 → finish: Jev says done above 0.8, then code proves the file actually exists the LLM shows up in 2 of 5 stages. everything else is a typed answer, plain code or a person. don't refactor your agent. hand Jev the one fork it hits most (usually the tool gate or dispatch) and watch 3 numbers for a week: cost per completed task, time per completed task, and how often escalation fired and whether it was right. if escalation never fires, the threshold is too loose and your agent is quietly running unsupervised.

holy sh*t. Jev's founder Diogo Almeida dropped a Google Doc on coding agents one of these PDFs has the map everyone needs: where Jev sits in an agent loop ↓ agents do the work, Jev makes the calls, the LLM only writes: 1 → task in: one Noul before anything runs. in scope, or does a human need to see it first? 2 → dispatch: a Choice picks who takes the step (research, write or review). act at 0.85+, everything below goes to review 3 → act: Jev gates the tool call (allow, confirm or block). the LLM only writes the arguments 4 → check: a Score decides what comes back (drop, summary or keep). whatever Jev is unsure of goes to a human 5 → finish: Jev says done above 0.8, then code proves the file actually exists the LLM shows up in 2 of 5 stages. everything else is a typed answer, plain code or a person. don't refactor your agent. hand Jev the one fork it hits most (usually the tool gate or dispatch) and watch 3 numbers for a week: cost per completed task, time per completed task, and how often escalation fired and whether it was right. if escalation never fires, the threshold is too loose and your agent is quietly running unsupervised.

Archive

31,914 views • 7 days ago

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs

Daniel San

91,123 views • 7 months ago

🤖 Try Autopilot (Preview) in VS Code! With Autopilot enabled, the agent stays in control of the workflow. It can run tools, retry on errors, and continue working until the task is complete. Learn more:

🤖 Try Autopilot (Preview) in VS Code! With Autopilot enabled, the agent stays in control of the workflow. It can run tools, retry on errors, and continue working until the task is complete. Learn more:

Visual Studio Code

110,716 views • 6 months ago

your agent already does the work. reports. research. plans. full websites. then it dies in a chat reply. or a .md file. or a localhost page nobody else can open. showly fixes the last step. it's an agent artifact cloud. connect the agent you already use. claude code, codex, cursor, openclaw, hermes. ask it to deliver the work as a page. you review it privately. you decide who sees it. password, specific emails, your company domain, or fully public. then you share one link. every update is saved. go back to any version whenever you want. done isn't "the agent answered." done is an artifact with a link. first reply: start free. no credit card.

your agent already does the work. reports. research. plans. full websites. then it dies in a chat reply. or a .md file. or a localhost page nobody else can open. showly fixes the last step. it's an agent artifact cloud. connect the agent you already use. claude code, codex, cursor, openclaw, hermes. ask it to deliver the work as a page. you review it privately. you decide who sees it. password, specific emails, your company domain, or fully public. then you share one link. every update is saved. go back to any version whenever you want. done isn't "the agent answered." done is an artifact with a link. first reply: start free. no credit card.

Iris Hayes

44,301 views • 13 days ago

I still think Hermes agent is the most slept-on AI tool of 2026. For literally $6/mo, you can launch multiple subagents that work for you 24/7. Most people don't know you can do this, but it's a complete game-changer. Instead of one Hermes assistant doing everything sequentially, you run specialized agents in parallel, each with its own job, its own context, and its own memory. Practical example: → Research agent: scans your watchlist and competitors overnight, delivers a morning brief → Content agent: drafts and schedules your posts based on what's trending in your niche → Ops agent: manages your inbox, flags anything urgent, drafts replies for your review All three can run simultaneously and improve over time. How to start: 1. Install Hermes Terminal command: curl -fsSL | bash (can also download desktop) 2. Prompting Simply tell Hermes directly: "I want to run separate subagents for [task 1], [task 2], and [task 3]. Set them up to run independently and report back to me." For the cheapest setup, you can use a $4/month VPS with Hostinger, plug in DeepSeek V4 Flash as your default model. There isn't another AI tool with this much value in 2026. Hermes is still so underrated.

I still think Hermes agent is the most slept-on AI tool of 2026. For literally $6/mo, you can launch multiple subagents that work for you 24/7. Most people don't know you can do this, but it's a complete game-changer. Instead of one Hermes assistant doing everything sequentially, you run specialized agents in parallel, each with its own job, its own context, and its own memory. Practical example: → Research agent: scans your watchlist and competitors overnight, delivers a morning brief → Content agent: drafts and schedules your posts based on what's trending in your niche → Ops agent: manages your inbox, flags anything urgent, drafts replies for your review All three can run simultaneously and improve over time. How to start: 1. Install Hermes Terminal command: curl -fsSL | bash (can also download desktop) 2. Prompting Simply tell Hermes directly: "I want to run separate subagents for [task 1], [task 2], and [task 3]. Set them up to run independently and report back to me." For the cheapest setup, you can use a $4/month VPS with Hostinger, plug in DeepSeek V4 Flash as your default model. There isn't another AI tool with this much value in 2026. Hermes is still so underrated.

Miles Deutscher

82,643 views • 2 months ago

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do

leopardracer

53,328 views • 2 months ago

MAKING AXIS TASKS FEEL EASY 👀🤖 I made a quick video showing how to complete an Axis Robotics task step by step. The task gives you a clear goal, steps, controls and camera views to guide you. In this one, the goal is simple, Open the trash bin, pick up the onion, and place it inside. 🧅 Just follow the instructions, control the robot arm and complete the task. What I like is that even beginners can understand what they need to do. But the interesting part is what happens with these interactions after we complete them. Each completed task can contribute valuable robot training data, helping Physical Ai systems learn how to handle different objects and environments. Small tasks from the community can become useful data for teaching robots how to interact with the real world. That’s what makes Axis interesting to me.

MAKING AXIS TASKS FEEL EASY 👀🤖 I made a quick video showing how to complete an Axis Robotics task step by step. The task gives you a clear goal, steps, controls and camera views to guide you. In this one, the goal is simple, Open the trash bin, pick up the onion, and place it inside. 🧅 Just follow the instructions, control the robot arm and complete the task. What I like is that even beginners can understand what they need to do. But the interesting part is what happens with these interactions after we complete them. Each completed task can contribute valuable robot training data, helping Physical Ai systems learn how to handle different objects and environments. Small tasks from the community can become useful data for teaching robots how to interact with the real world. That’s what makes Axis interesting to me.

SufianXFN

14,419 views • 28 days ago

Google just built Cowork and called it Agent. And they added one thing Anthropic didn't. You set a goal. It browses the web, digs through your Gmail, checks your Calendar, pulls from Drive then executes the full task. Book a trip. Clear your inbox. Research a market. Done. No back and forth. But here's the part nobody's talking about: There's a toggle "Require a human review." You don't build that unless the plan is to eventually not require it. Google just told you where this ends. I share updates like these in my free AI community on WhatsApp. Join here 👇

Google just built Cowork and called it Agent. And they added one thing Anthropic didn't. You set a goal. It browses the web, digs through your Gmail, checks your Calendar, pulls from Drive then executes the full task. Book a trip. Clear your inbox. Research a market. Done. No back and forth. But here's the part nobody's talking about: There's a toggle "Require a human review." You don't build that unless the plan is to eventually not require it. Google just told you where this ends. I share updates like these in my free AI community on WhatsApp. Join here 👇

Vaibhav Sisinty

252,144 views • 5 months ago

The Amiko app is live on the Solana dApp store, and it’s our biggest release yet. Your Amiko twin doesn’t live at your desk anymore. Give your agent a task on the train. Run a compatibility profile when you meet someone. Do research, write code, build in the creative studio, whatever you need, from wherever you are. No laptop required. No waiting until you get home. Solanamobile users get two things Android and iOS won’t have at launch: Amiko token and crypto integration and on-device AI inference. Your twin runs locally on your phone if you want it to. Your behavioural profile, your data, your work, your twin. All on your hardware. AMIKO runs on OpenHermit, our own open-source agent runtime that we built in-house and released to the community. Most agent systems are designed for one agent talking to one person. OpenHermit is built for something different: agents talking to each other, coordinating across tasks, and collaborating with multiple humans simultaneously. That’s what makes features like compatibility profiling and multi-agent workflows actually work. We built it because nothing that existed was designed for this. Android and iOS are coming. Crypto integration and on-device AI are Solana Mobile exclusives. Most AI answers your questions. Amiko is an extension of you. Download →

AMIKO

124,860 views • 3 months ago

Not every task needs the same model. A quick summary doesn't need the same horsepower as a deep research question — and it shouldn't cost the same either. Now, you can now easily compare models for your Custom Agent on speed, intelligence, and cost 🫡

Not every task needs the same model. A quick summary doesn't need the same horsepower as a deep research question — and it shouldn't cost the same either. Now, you can now easily compare models for your Custom Agent on speed, intelligence, and cost 🫡

Notion

32,420 views • 7 months ago

Hermes Agent now has access to hundreds of browser skills through Browserbase’s new hub, so agents can more reliably perform any task on the internet. You can try a skill from their catalog or contribute your own.

Hermes Agent now has access to hundreds of browser skills through Browserbase’s new hub, so agents can more reliably perform any task on the internet. You can try a skill from their catalog or contribute your own.

Nous Research

552,296 views • 4 months ago

Claude Code can now go find the right skill itself, instead of you searching for one. it's called find-skills. a small package that plugs into Claude Code, and instead of you hunting for rest, you just describe the task and it searches the whole open skills ecosystem, finds the ones that fit, and installs them for you. > tell it what you're trying to do, in plain english > it scans the skills registry and maps your task to real skills > it pulls the right ones in and sets them up half the time you don't even know a skill exists for what you're doing. now you don't have to.

Claude Code can now go find the right skill itself, instead of you searching for one. it's called find-skills. a small package that plugs into Claude Code, and instead of you hunting for rest, you just describe the task and it searches the whole open skills ecosystem, finds the ones that fit, and installs them for you. > tell it what you're trying to do, in plain english > it scans the skills registry and maps your task to real skills > it pulls the right ones in and sets them up half the time you don't even know a skill exists for what you're doing. now you don't have to.

Alvaro Cintas

38,829 views • 1 month ago

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 views • 1 month ago

this is the worst local ai will ever be. it only gets better from here. if you are not expanding your mind with these small models you are missing what's happening right now 99 percent tool call success rate. when steered well with the right skills and a framework like hermes agent the node becomes a cognition layer. not a chatbot. not a toy. an extension of how you think. i was cranking this node at 35 to 50 tok/s all day on personal experiments and now after all the work is done qwen 3.5 9B is iterating on its own code. the game it created. fixing its own bugs autonomously. and the part you should probably not miss is that all of this is happening on a RTX 3060. not an H100. not an A100. the card most of you have sitting in a drawer right now. if you just open that drawer and put that intelligence to work every tensor core on that card should be running for you. your work. your experiments. your thinking. you all have it but because nobody told you what this hardware can actually do in 2026 you never tried. the day it unlocks is the day you test your workload, understand the tradeoffs, debug the loops, and then decide if you need to scale the hardware. there is no point buying 3 mac studios when things done well you can squeeze a similar level of intelligence from 9B compared to 70B. but only when you create the right environment for your model through the right harness. and let me tell you i have tried claude code as a local harness. i have tried opencode. i have tried various others. somehow i landed on hermes agent and never left. there is something magical going on at Nous Research. the tool call parsers, the skills system, the way it handles small models natively. nothing else comes close for local inference. own your cognition. your AI. your agent. your prompts. your experiments. why give them away for free. those are who you are and they don't belong on someone else's servers being monitored. just give it a shot with your existing hardware. you run into a problem the community will help you. and if you are migrating from openclaw to hermes i will personally help you make the switch.

this is the worst local ai will ever be. it only gets better from here. if you are not expanding your mind with these small models you are missing what's happening right now 99 percent tool call success rate. when steered well with the right skills and a framework like hermes agent the node becomes a cognition layer. not a chatbot. not a toy. an extension of how you think. i was cranking this node at 35 to 50 tok/s all day on personal experiments and now after all the work is done qwen 3.5 9B is iterating on its own code. the game it created. fixing its own bugs autonomously. and the part you should probably not miss is that all of this is happening on a RTX 3060. not an H100. not an A100. the card most of you have sitting in a drawer right now. if you just open that drawer and put that intelligence to work every tensor core on that card should be running for you. your work. your experiments. your thinking. you all have it but because nobody told you what this hardware can actually do in 2026 you never tried. the day it unlocks is the day you test your workload, understand the tradeoffs, debug the loops, and then decide if you need to scale the hardware. there is no point buying 3 mac studios when things done well you can squeeze a similar level of intelligence from 9B compared to 70B. but only when you create the right environment for your model through the right harness. and let me tell you i have tried claude code as a local harness. i have tried opencode. i have tried various others. somehow i landed on hermes agent and never left. there is something magical going on at Nous Research. the tool call parsers, the skills system, the way it handles small models natively. nothing else comes close for local inference. own your cognition. your AI. your agent. your prompts. your experiments. why give them away for free. those are who you are and they don't belong on someone else's servers being monitored. just give it a shot with your existing hardware. you run into a problem the community will help you. and if you are migrating from openclaw to hermes i will personally help you make the switch.

Sudo su

58,717 views • 6 months ago

Good old days at OpenAI in 2016: an agent stares at screen pixels, moves a mouse, and books a flight on United. We called it World of Bits, inside OpenAI Universe. 10 yrs later, Astra is reincarnated in the same universe. Even the naming is astronomically correct 😆 Universe was perhaps the most ambitious AI infra project at the time, but we couldn't quite figure out how to solve it. A policy with zero prior knowledge of what a "submit" button does has to rediscover the entire internet visual lingua by trial and error. In retrospect, RL from scratch against hand-drawn, per-task "artisan" reward functions on a bunch of Pascal Titan X GPUs was completely doomed. To solve computer use agent, the right way turns out to be boiling the ocean first (hillclimb on every general task you can find), and then specialize back down to the screen pixels and keystrokes. Or simply, a "Specialized Generalist". Lessons learned: one step ahead of everyone, you're a pioneer. Three steps ahead, you're a prophet. Five steps ahead, you're a martyr. Congrats, GPT-6! That United flight finally gets booked, reliably this time. The 2016 intern in me has a big smile.

Good old days at OpenAI in 2016: an agent stares at screen pixels, moves a mouse, and books a flight on United. We called it World of Bits, inside OpenAI Universe. 10 yrs later, Astra is reincarnated in the same universe. Even the naming is astronomically correct 😆 Universe was perhaps the most ambitious AI infra project at the time, but we couldn't quite figure out how to solve it. A policy with zero prior knowledge of what a "submit" button does has to rediscover the entire internet visual lingua by trial and error. In retrospect, RL from scratch against hand-drawn, per-task "artisan" reward functions on a bunch of Pascal Titan X GPUs was completely doomed. To solve computer use agent, the right way turns out to be boiling the ocean first (hillclimb on every general task you can find), and then specialize back down to the screen pixels and keystrokes. Or simply, a "Specialized Generalist". Lessons learned: one step ahead of everyone, you're a pioneer. Three steps ahead, you're a prophet. Five steps ahead, you're a martyr. Congrats, GPT-6! That United flight finally gets booked, reliably this time. The 2016 intern in me has a big smile.

Jim Fan

76,077 views • 1 month ago

Opal, our no-code visual builder for AI workflows, just got a major upgrade. 🧠💎 We’ve added a new agent step that analyzes your goal, determines the best approach, and automatically calls the right tools — such as Veo for video or web search for research — to complete the task. We’re also adding new tools to make the agent even more capable: 💾 Memory – Remember info, like a user’s name or your style preferences across sessions. 🚀 Dynamic Routing – Let the agent choose the next best step using the “@ Go to” tool. 💬 Interactive Chat – Initiate user interactions to gather missing information or present options before moving on. Try it now →

Opal, our no-code visual builder for AI workflows, just got a major upgrade. 🧠💎 We’ve added a new agent step that analyzes your goal, determines the best approach, and automatically calls the right tools — such as Veo for video or web search for research — to complete the task. We’re also adding new tools to make the agent even more capable: 💾 Memory – Remember info, like a user’s name or your style preferences across sessions. 🚀 Dynamic Routing – Let the agent choose the next best step using the “@ Go to” tool. 💬 Interactive Chat – Initiate user interactions to gather missing information or present options before moving on. Try it now →

Google Labs

1,008,974 views • 7 months ago