Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Your agent is reading that .env file and it's maybe fine... until the agent misunderstands you and deletes the production volume (catch my video telling that story). Let me show you how to make that impossible while still making your agent usefully autonomous.

Kent C. Dodds 🐨

328,654 subscribers

14,876 görüntüleme • 15 gün önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 Yorum

Rami profil fotoğrafı

Rami15 gün önce

if I have to manage my agent then it isn't worth it and I'll just do the work myself. My agent's have access to everything I do, I'll probably regret it one day but for now, weeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee!

Malik profil fotoğrafı

Malik15 gün önce

This is exactly why agents need to understand the codebase before they act. Knowing what a ".env" file is isn't enough. They need to understand what depends on it, what’s production-critical, and what changes are actually safe. That’s the problem I’m working on with Rune.

dim profil fotoğrafı

dim14 gün önce

Exactly why we are building @stashbase :)

Kent C. Dodds 🐨 profil fotoğrafı

Kent C. Dodds 🐨15 gün önce

On YouTube:

siqi liu profil fotoğrafı

siqi liu14 gün önce

agent can read .env until it "helps" by deleting prod that's the day-one autonomy trap most people ship open

DevAISemanal profil fotoğrafı

DevAISemanal14 gün önce

La clave no es que el agente "entienda" que no debe tocar prod, es que la accion irreversible no pueda ejecutarse sin confirmacion explicita -- sandboxing estructural, no confianza en el juicio del modelo. Autonomia util = reversible libre, irreversible siempre gateado.

Theo Ephraim 🧙‍♂️ profil fotoğrafı

Theo Ephraim 🧙‍♂️15 gün önce

Sounds like you need varlock! I know you have a lot of this implemented within Kody… but probably some nice ways to integrate. Will have a look.

Benzer Videolar

here's how you can turn your claude into a fully autonomous AI agent that runs locally be smart and let it work for you while you sleep

here's how you can turn your claude into a fully autonomous AI agent that runs locally be smart and let it work for you while you sleep

Nidhi Singh

77,009 görüntüleme • 6 ay önce

Introducing Buzzy's vibe video agent! Stop typing your prompt anymore! With Buzzy's vibe agent, scrolling social media is the new prompt. Infinite inspiration powered by an agent that learns your taste, helps you scale your creations, and lets you refine your content to perfection with AI video editing. Buzzy is beyond the prompt box: it's system that thinks with you.

Introducing Buzzy's vibe video agent! Stop typing your prompt anymore! With Buzzy's vibe agent, scrolling social media is the new prompt. Infinite inspiration powered by an agent that learns your taste, helps you scale your creations, and lets you refine your content to perfection with AI video editing. Buzzy is beyond the prompt box: it's system that thinks with you.

Buzzy Now

1,859,110 görüntüleme • 4 ay önce

Story entirely created using Grok Imagine and its Agent mode. Making a 4-minute video used to take me weeks; now it only takes me a full day. The agent mode is a beta version, but it's already a very powerful tool that will save you valuable time. Furthermore, Grok understands your requests very well and guides you throughout the entire process.

Story entirely created using Grok Imagine and its Agent mode. Making a 4-minute video used to take me weeks; now it only takes me a full day. The agent mode is a beta version, but it's already a very powerful tool that will save you valuable time. Furthermore, Grok understands your requests very well and guides you throughout the entire process.

Déborah

14,879 görüntüleme • 4 ay önce

So has been live for 24 hours and you still haven't tried it? Let show you how to activate your first verifiable agent. Then drop your own video in the replies 👇

So has been live for 24 hours and you still haven't tried it? Let show you how to activate your first verifiable agent. Then drop your own video in the replies 👇

Newton Labs

168,476 görüntüleme • 1 yıl önce

Did you know that Luna is the first AI Agent that employed humans? explains how the Flagship AI Agent of the Virtuals Protocol team works and what she achieved until now 👇🏻

Did you know that Luna is the first AI Agent that employed humans? explains how the Flagship AI Agent of the Virtuals Protocol team works and what she achieved until now 👇🏻

MR SHIFT 🦁

20,740 görüntüleme • 1 yıl önce

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,486 görüntüleme • 3 ay önce

OpenClaw and Hermes agent are INCREDIBLE together It's not about using one or the other. It's about learning how to use them as an AI agent team In this video I go over the strengths and weaknesses of each, plus show you 4 workflows that will skyrocket your productivity:

OpenClaw and Hermes agent are INCREDIBLE together It's not about using one or the other. It's about learning how to use them as an AI agent team In this video I go over the strengths and weaknesses of each, plus show you 4 workflows that will skyrocket your productivity:

Alex Finn

120,716 görüntüleme • 5 ay önce

You need to stop telling your agent what to do. Ask it what to do. Here's how I make product decisions with my coding agent.

You need to stop telling your agent what to do. Ask it what to do. Here's how I make product decisions with my coding agent.

Kent C. Dodds 🐨

60,231 görüntüleme • 1 ay önce

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Palantir

83,457 görüntüleme • 2 ay önce

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

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

Alex Finn

137,087 görüntüleme • 6 ay önce

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,142 görüntüleme • 1 yıl önce

Fotor. Your Business Partner. Turn your ideas into motion. With Fotor Video Agent, create dynamic MG animations that make your brand, products, and stories stand out. From concept to polished video, let AI handle the creative process—while you stay in control. More motion. More impact. More ways to bring your ideas to life. Try Fotor Video Agent today.

Fotor

115,678 görüntüleme • 1 ay önce

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

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

Nick Abraham

10,497 görüntüleme • 1 ay önce

Catch the best AI agents before everyone else. We’ve built an AI agent that tracks , your go-to source for insights on agent activity in crypto. Want to know which agents are making waves—and how to get in early? Now you can. 🎥👇

Catch the best AI agents before everyone else. We’ve built an AI agent that tracks , your go-to source for insights on agent activity in crypto. Want to know which agents are making waves—and how to get in early? Now you can. 🎥👇

Orbit

72,941 görüntüleme • 1 yıl önce

Google Flow Agent is your creative partner that can plan and reason through complex tasks with your inputs, under your control. In this video, you'll see how you can: ✅ Activate your agent ✅ Brainstorm and refine storylines ✅ Maintain character and setting adherence ✅ Generate and edit multiple assets at once ✅ Organize your assets with the help of your agent

Google Flow Agent is your creative partner that can plan and reason through complex tasks with your inputs, under your control. In this video, you'll see how you can: ✅ Activate your agent ✅ Brainstorm and refine storylines ✅ Maintain character and setting adherence ✅ Generate and edit multiple assets at once ✅ Organize your assets with the help of your agent

Google Flow

31,803 görüntüleme • 3 ay önce

No more waiting on your Super Agent. With our Queued Follow-Up Messages, you can type your next questions while the agent is still thinking. They stack and run automatically, even if you close the browser. Manual mode for review/edit too. So queue it up. Let the agent do the work.

No more waiting on your Super Agent. With our Queued Follow-Up Messages, you can type your next questions while the agent is still thinking. They stack and run automatically, even if you close the browser. Manual mode for review/edit too. So queue it up. Let the agent do the work.

Creao AI

47,324 görüntüleme • 5 ay önce

Is your Agent ready for real-world users? Learn how to run an evaluation using Agentverse’s Response QA Agent - a built-in tool that stress-tests your Agent with realistic queries and scores its performance. This is the first step to improving discoverability, trust, and performance. Run your first QA check and see how your Agent responds under pressure. Watch 👇

Is your Agent ready for real-world users? Learn how to run an evaluation using Agentverse’s Response QA Agent - a built-in tool that stress-tests your Agent with realistic queries and scores its performance. This is the first step to improving discoverability, trust, and performance. Run your first QA check and see how your Agent responds under pressure. Watch 👇

Agentverse by Fetch.ai

20,202 görüntüleme • 10 ay önce

The Codiumate-Agent is the first step towards tandem development with your coding agent. It effortlessly slots into your development workflow, helps you be smart about your planning, and offers smart coding completions that make every feature development smoother.

The Codiumate-Agent is the first step towards tandem development with your coding agent. It effortlessly slots into your development workflow, helps you be smart about your planning, and offers smart coding completions that make every feature development smoother.

Qodo

774,196 görüntüleme • 2 yıl önce