Loading video...

Video Failed to Load

Go Home

BREAKING: OpenAI has officially released Agent Mode, allowing users to spin up a virtual desktop and take action. I got early access to ChatGPT Agent Mode and want to share my thoughts. Agent Mode lets you delegate tasks like searching or browsing to an agent inside a virtual desktop...

alliekmiller's profile picture

Allie K. Miller

103,623 subscribers

155,943 views • 1 year ago •via X (Twitter)

Science & TechnologyNews & PoliticsEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

BREAKING 🚨: OpenAI released Atlas, a new AI browser with Memory recall and native Agent Mode. I had a chance to run many tests with Atlas and will share them shortly as well. - Atlas is fully integrated with ChatGPT and powered by ChatGPT search. - Agent Mode can navigate web pages for you, and you can spawn as many Agent Mode tabs as you wish. It is now available to Free, Plus, Pro, Go, and Business users worldwide. Enterprise and Education customers can access a beta if enabled by their admin. Versions for Windows, iOS, and Android are in development.
0:58

BREAKING 🚨: OpenAI released Atlas, a new AI browser with Memory recall and native Agent Mode. I had a chance to run many tests with Atlas and will share them shortly as well. - Atlas is fully integrated with ChatGPT and powered by ChatGPT search. - Agent Mode can navigate web pages for you, and you can spawn as many Agent Mode tabs as you wish. It is now available to Free, Plus, Pro, Go, and Business users worldwide. Enterprise and Education customers can access a beta if enabled by their admin. Versions for Windows, iOS, and Android are in development.

TestingCatalog News 🗞

96,341 views • 9 months ago

At Postman, we have adopted an AI-native mindset to product development. What does this mean in practice? Just like you can generate text with AI, Postman's Agent Mode can generate a UI as well. Case in point: we have added the ability to review, generate, and change diffs for important changes right inside agent mode's chat interaction. If the user trusts agent mode, they can continue in auto-mode, but for critical changes, they can have the agent mode inform the user, review what is changing, and then give the go ahead to approve. See this in action below in the video! While there is a lot of focus on AI generated code today, I believe a large chunk of pre-built UI work will just go away and micro-interactions and workflow steps will be created on the fly through a combination of AI + APIs. How to operate in this new world? Build your API first. Hook it up to AI. If your users really want the UI every time, invest in the GUI.
0:30

At Postman, we have adopted an AI-native mindset to product development. What does this mean in practice? Just like you can generate text with AI, Postman's Agent Mode can generate a UI as well. Case in point: we have added the ability to review, generate, and change diffs for important changes right inside agent mode's chat interaction. If the user trusts agent mode, they can continue in auto-mode, but for critical changes, they can have the agent mode inform the user, review what is changing, and then give the go ahead to approve. See this in action below in the video! While there is a lot of focus on AI generated code today, I believe a large chunk of pre-built UI work will just go away and micro-interactions and workflow steps will be created on the fly through a combination of AI + APIs. How to operate in this new world? Build your API first. Hook it up to AI. If your users really want the UI every time, invest in the GUI.

Abhinav Asthana

104,263 views • 1 year ago

these guys are making Claude, Hermes, and DeepSeek argue with each other instead of just agreeing with you. this is the practical future of agent teams. with Bloome you just pick a task template, and it spins up a full agent team in a group chat to collaborate and get the job done. research, review, writing, market analysis, or anything you want. they brainstorm, review, and plan together. meanwhile, you or other human teammates can steer them or jump in, and stay in the same conversation so nothing gets lost across tools. since this is actual work, Bloome works across web, mobile, and desktop. try the desktop app first if you're using it seriously. same flexibility on the agent side too, you can connect any agents you want: ChatGPT, OpenClaw, Gemini… check them out →
0:58

these guys are making Claude, Hermes, and DeepSeek argue with each other instead of just agreeing with you. this is the practical future of agent teams. with Bloome you just pick a task template, and it spins up a full agent team in a group chat to collaborate and get the job done. research, review, writing, market analysis, or anything you want. they brainstorm, review, and plan together. meanwhile, you or other human teammates can steer them or jump in, and stay in the same conversation so nothing gets lost across tools. since this is actual work, Bloome works across web, mobile, and desktop. try the desktop app first if you're using it seriously. same flexibility on the agent side too, you can connect any agents you want: ChatGPT, OpenClaw, Gemini… check them out →

ℏεsam

61,952 views • 10 days ago

Real estate agent and brokers. The recent ruling in Missouri is wrong, will only benefit litigators, ambulance, tracers, and I believe will be appealed. More importantly, this ruling will not negatively impact housing or buyers agents unless you allowed to iMessage to all homebuyers I have never as a professional real estate investor not used a buyers agent to represent me in a transaction. Even when the deal was off market, I hired an agent to represent me to make sure that all my rights were protected and that I got the best price. If you pay a bar’s agent is nothing compared to what they can get done for you as a buyer, I will never ask for a discount. I will always use the agent to go get that discount for me more importantly, or as importantly, I will always use the agent to keep the deal together. The purpose of the buyers agent is to find the right or best property in the right or best location at the right time at the best price. If you’re not using your buyer’s agent to achieve that or you’re hiring the wrong agent well, that’s on you. Hire the right agent pay them well and make them do their job. It will be well worth the money. #RealEstate #Buyers #BuyerAgent #RealEstateRuling #Commission
1:30

Real estate agent and brokers. The recent ruling in Missouri is wrong, will only benefit litigators, ambulance, tracers, and I believe will be appealed. More importantly, this ruling will not negatively impact housing or buyers agents unless you allowed to iMessage to all homebuyers I have never as a professional real estate investor not used a buyers agent to represent me in a transaction. Even when the deal was off market, I hired an agent to represent me to make sure that all my rights were protected and that I got the best price. If you pay a bar’s agent is nothing compared to what they can get done for you as a buyer, I will never ask for a discount. I will always use the agent to go get that discount for me more importantly, or as importantly, I will always use the agent to keep the deal together. The purpose of the buyers agent is to find the right or best property in the right or best location at the right time at the best price. If you’re not using your buyer’s agent to achieve that or you’re hiring the wrong agent well, that’s on you. Hire the right agent pay them well and make them do their job. It will be well worth the money. #RealEstate #Buyers #BuyerAgent #RealEstateRuling #Commission

Grant Cardone

51,494 views • 2 years ago

Over the past couple of years, you’ve heard us reference “agents” and “agentic capabilities,” nebulous concepts that are designed to help you with coding, booking trips, and other complex multi-step tasks. But, what actually IS an agent? We think of AI agents as systems that combine the intelligence of advanced AI models with access to tools so they can take actions on your behalf, under your control. Whether it’s a coding agent or our recently unveiled experimental tool Gemini Agent in the Google Gemini, these are systems that will meet you where you are, in the products that you love, to help take the tedious tasks you want off your plate.
0:57

Over the past couple of years, you’ve heard us reference “agents” and “agentic capabilities,” nebulous concepts that are designed to help you with coding, booking trips, and other complex multi-step tasks. But, what actually IS an agent? We think of AI agents as systems that combine the intelligence of advanced AI models with access to tools so they can take actions on your behalf, under your control. Whether it’s a coding agent or our recently unveiled experimental tool Gemini Agent in the Google Gemini, these are systems that will meet you where you are, in the products that you love, to help take the tedious tasks you want off your plate.

Google AI

120,790 views • 7 months ago

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 views • 1 year ago

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.
0:44

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Arena.ai

344,089 views • 1 month ago

Introducing Vault Mode 🔒 👾 Vault Mode enables creators to tokenize and gate access to their agents and prompts. With Vault Mode, you can require users to hold your agent tokens before they can access your products. If a user does not hold the required tokens, access is automatically restricted. This unlocks an entirely new monetization model for the agent economy allowing creators to build token-gated agents, premium prompts, exclusive tools, private swarms, and more. Learn more ⬇️🧵
1:06

Introducing Vault Mode 🔒 👾 Vault Mode enables creators to tokenize and gate access to their agents and prompts. With Vault Mode, you can require users to hold your agent tokens before they can access your products. If a user does not hold the required tokens, access is automatically restricted. This unlocks an entirely new monetization model for the agent economy allowing creators to build token-gated agents, premium prompts, exclusive tools, private swarms, and more. Learn more ⬇️🧵

swarms

21,052 views • 1 month ago

Introducing Agent Wikis! I've been using llm wikis (or knowledge bases) for research and videos for a while to ensure the information I'm providing is always up-to-date and accurate. Now you can access them for free! Just point your agent at to access wikis on many topics, including Hermes Agent, Hyperframes, Google Ads, and llama.cpp. They can be queried through a simple MCP server. Everything has been designed to be agent-friendly and lightweight (no context bloat). This is a beta release, so please let me know of any bugs or issues (I'm sure there are one or two). You can also join the waitlist if you would like us to create and maintain your own private wiki, or if you are a project owner you can request one for your project to make sure your users (and their agents) don't run into any common issues (and also be featured on the site). Thank you!
0:30

Introducing Agent Wikis! I've been using llm wikis (or knowledge bases) for research and videos for a while to ensure the information I'm providing is always up-to-date and accurate. Now you can access them for free! Just point your agent at to access wikis on many topics, including Hermes Agent, Hyperframes, Google Ads, and llama.cpp. They can be queried through a simple MCP server. Everything has been designed to be agent-friendly and lightweight (no context bloat). This is a beta release, so please let me know of any bugs or issues (I'm sure there are one or two). You can also join the waitlist if you would like us to create and maintain your own private wiki, or if you are a project owner you can request one for your project to make sure your users (and their agents) don't run into any common issues (and also be featured on the site). Thank you!

tonbi

43,798 views • 1 month ago

🚀 Introducing Queue: A Smarter Way to Build with Replit Agent Today, we’re excited to launch Queue, a powerful new capability designed to enhance your experience with Replit Agent. With Queue, you can submit multiple tasks while your Agent is still working—no more waiting around or breaking your flow. As each task completes, the Agent automatically moves to the next. You can: ✅ Add multiple tasks for the Agent to process in order. ✅ Edit, reorder, or reprioritize messages on the fly. ✅ Attach files and adjust settings—including toggling extended thinking or selecting a different model—per task.
0:27

🚀 Introducing Queue: A Smarter Way to Build with Replit Agent Today, we’re excited to launch Queue, a powerful new capability designed to enhance your experience with Replit Agent. With Queue, you can submit multiple tasks while your Agent is still working—no more waiting around or breaking your flow. As each task completes, the Agent automatically moves to the next. You can: ✅ Add multiple tasks for the Agent to process in order. ✅ Edit, reorder, or reprioritize messages on the fly. ✅ Attach files and adjust settings—including toggling extended thinking or selecting a different model—per task.

Replit ⠕

75,576 views • 1 year ago

Now you can use your favorite AI agent to control your Coinbase account (or a sub-account), with Coinbase for Agents. Here’s a quick demo on how to set it up and some of the cool things you can get your agent to do.
3:17

Now you can use your favorite AI agent to control your Coinbase account (or a sub-account), with Coinbase for Agents. Here’s a quick demo on how to set it up and some of the cool things you can get your agent to do.

Brian Armstrong

212,376 views • 1 month ago

Hermes Agent with ChatGPT 5.5 is literally magic I've thrown some of my hardest tasks at this combo and the agent has been able to handle EVERYTHING In this video I take you through EVERYTHING Hermes from how to set it up to awesome use cases Time to set up your AI employee:
17:16

Hermes Agent with ChatGPT 5.5 is literally magic I've thrown some of my hardest tasks at this combo and the agent has been able to handle EVERYTHING In this video I take you through EVERYTHING Hermes from how to set it up to awesome use cases Time to set up your AI employee:

Alex Finn

117,750 views • 2 months ago

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!
2:55

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

fxnction

27,570 views • 1 month ago

Tempo's Dan Romero explains why the future of AI agents will be "stablecoin-native." John: "Why wouldn't I just give OpenClaw my credit card?" Dan Romero: "The credit card itself is kind of a private key, having that get prompt-injected out, maybe not the best thing in the world." “If you have agent swarms, the idea of spinning up a new credit card for each individual sub-agent doesn’t make sense. With wallets, you can spin up as many as you want and manage the balances for each agent.” “An API call to any of these frontier labs right now is pay-per-call. You’re eventually going to get to a point where, for every single API call, you can just pay some amount of stablecoins in the background and keep moving.”
1:39

Tempo's Dan Romero explains why the future of AI agents will be "stablecoin-native." John: "Why wouldn't I just give OpenClaw my credit card?" Dan Romero: "The credit card itself is kind of a private key, having that get prompt-injected out, maybe not the best thing in the world." “If you have agent swarms, the idea of spinning up a new credit card for each individual sub-agent doesn’t make sense. With wallets, you can spin up as many as you want and manage the balances for each agent.” “An API call to any of these frontier labs right now is pay-per-call. You’re eventually going to get to a point where, for every single API call, you can just pay some amount of stablecoins in the background and keep moving.”

TBPN

41,347 views • 4 months ago

I’m usually skeptical of “AI workspace” products, but Bloome has a few ideas I actually like: You can put humans + multiple agents in the same conversation. One agent can draft something, another can poke holes in it, and another can clean up the final version. You can also bring in different agents/models like Claude, ChatGPT, DeepSeek, etc. instead of constantly bouncing between tabs. And because the whole conversation stays in context, teammates can join later and still understand how the work got to the final output. It also works across web, desktop, and mobile, though if you’re using it for real work, I’d especially recommend trying the desktop app. Feels closer to how real teams actually work.
0:44

I’m usually skeptical of “AI workspace” products, but Bloome has a few ideas I actually like: You can put humans + multiple agents in the same conversation. One agent can draft something, another can poke holes in it, and another can clean up the final version. You can also bring in different agents/models like Claude, ChatGPT, DeepSeek, etc. instead of constantly bouncing between tabs. And because the whole conversation stays in context, teammates can join later and still understand how the work got to the final output. It also works across web, desktop, and mobile, though if you’re using it for real work, I’d especially recommend trying the desktop app. Feels closer to how real teams actually work.

AI Breakfast

76,746 views • 5 days ago

Today, we’re excited to announce AI Actions! AI Actions turn your chatbot into an AI Agent that can take actions by calling any API. This lets the agent do things like upgrade_subscription, track_shipment, book_appointment, and more. Here’s how it works: 1. Set up your API in Chatbase or select from prebuilt actions like Cal.com get_available_slots and Matt Slack send_message. 2. Provide a prompt to guide the Agent on when and how to use the action. 3. Your AI Agent takes care of the rest, executing actions for your customers, giving them a mind-blowing experience. These actions can be internal APIs for app-specific tasks or it can be APIs for external tools your business uses like a ticketing system, a CRM, e-commerce platform, or really anything else. We're raising the bar for customer experience.
0:40

Today, we’re excited to announce AI Actions! AI Actions turn your chatbot into an AI Agent that can take actions by calling any API. This lets the agent do things like upgrade_subscription, track_shipment, book_appointment, and more. Here’s how it works: 1. Set up your API in Chatbase or select from prebuilt actions like Cal.com get_available_slots and Matt Slack send_message. 2. Provide a prompt to guide the Agent on when and how to use the action. 3. Your AI Agent takes care of the rest, executing actions for your customers, giving them a mind-blowing experience. These actions can be internal APIs for app-specific tasks or it can be APIs for external tools your business uses like a ticketing system, a CRM, e-commerce platform, or really anything else. We're raising the bar for customer experience.

Chatbase

410,583 views • 1 year ago

Tempo's Dan Romero explains why the future of AI agents will be "stablecoin-native." John: "Why wouldn't I just give OpenClaw my credit card?" Dan Romero: "The credit card itself is kind of a private key, having that get prompt-injected out, maybe not the best thing in the world." “If you have agent swarms, the idea of spinning up a new credit card for each individual sub-agent doesn’t make sense. With wallets, you can spin up as many as you want and manage the balances for each agent.” “An API call to any of these frontier labs right now is pay-per-call. You’re eventually going to get to a point where, for every single API call, you can just pay some amount of stablecoins in the background and keep moving.”
1:39

Tempo's Dan Romero explains why the future of AI agents will be "stablecoin-native." John: "Why wouldn't I just give OpenClaw my credit card?" Dan Romero: "The credit card itself is kind of a private key, having that get prompt-injected out, maybe not the best thing in the world." “If you have agent swarms, the idea of spinning up a new credit card for each individual sub-agent doesn’t make sense. With wallets, you can spin up as many as you want and manage the balances for each agent.” “An API call to any of these frontier labs right now is pay-per-call. You’re eventually going to get to a point where, for every single API call, you can just pay some amount of stablecoins in the background and keep moving.”

TBPN

155,348 views • 5 months ago

THIS GUY IS RUNNING A 5-AGENT OPENCLAW TEAM 24/7 FOR UNDER $50 A MONTH five agents all running continuously and handing tasks to each other > research agent tracking trends and competitors > writing agent handling marketing content and drafts > ops agent managing emails and scheduling > monitoring agent watching for alerts and updates > coordinator agent routing tasks between all of them and he built a full 3D isometric office where you can watch all of them work in real time and see the current task that each agent is doing each agent has a character, a desk, and a name tag. when it's time for a standup, they walk to the meeting room and gather which is insane it even has voice connection. you can talk to the agents through speech-to-text and tell them what to do out loud it's a tiny autonomous team that runs itself. the coordinator decides who handles what and tasks get passed between agents automatically. it never stops and runs 24/7 all for less than $50/month. we went from AI tools a few months back to AI employees real fast
0:57

THIS GUY IS RUNNING A 5-AGENT OPENCLAW TEAM 24/7 FOR UNDER $50 A MONTH five agents all running continuously and handing tasks to each other > research agent tracking trends and competitors > writing agent handling marketing content and drafts > ops agent managing emails and scheduling > monitoring agent watching for alerts and updates > coordinator agent routing tasks between all of them and he built a full 3D isometric office where you can watch all of them work in real time and see the current task that each agent is doing each agent has a character, a desk, and a name tag. when it's time for a standup, they walk to the meeting room and gather which is insane it even has voice connection. you can talk to the agents through speech-to-text and tell them what to do out loud it's a tiny autonomous team that runs itself. the coordinator decides who handles what and tasks get passed between agents automatically. it never stops and runs 24/7 all for less than $50/month. we went from AI tools a few months back to AI employees real fast

Om Patel

27,131 views • 3 months ago

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.
1:18

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,370 views • 1 month ago

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.
2:14

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

Aaron Levie

24,618 views • 3 months ago