Video yükleniyor...

Video Yüklenemedi

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

Ana Sayfaya Dön

🚨BREAKING: This Sequoia-backed company just destroyed Devin, OpenAI’s Codex, and Cursor. Imagine giving your dev team 3x velocity overnight. That’s what Factory’s new Droids are doing for teams at Zapier, MongoDB, and more. Factory just launched software agents agents called Droids that write code, close tickets, and deliver docs... show more

Tulsi Soni

151,267 subscribers

54,326 görüntüleme • 1 yıl önce •via X (Twitter)

Haberler & Politika Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

11 Yorum

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

: Your new engineering powerhouse in every tab. Explaining and helping you understand, mastering PR reviews, and optimizing operations. All while seamlessly integrating like a seasoned team member.

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

Seamless coding Craft production-ready features from any ticket, spec, or prompt

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

Incident Resolution Dive deep into incident investigations, craft insightful RCAs, and masterfully debug intricate multi-service systems.

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

Master Your Codebase Unlock the intricacies of your entire codebase with Factory's powerful research tools.

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

Create PRDs in a Snap Tag Droids in Slack, and watch them craft a PRD using the conversation context.

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

Linear Management Simplify your workflow with Factory's automatic ticket handling.

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

Review PRs Review PRs thoroughly, ensuring code quality and alignment with project goals, while fostering collaboration and providing constructive feedback to enhance team productivity.

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

Give it a go at:

Tulsi Soni profil fotoğrafı

Tulsi Soni1 yıl önce

I hope you've found this thread helpful. Follow me @shedntcare_ for more. Like/Repost the quote below if you can:

Greg Caplan 🚀 profil fotoğrafı

Greg Caplan 🚀2 yıl önce

Stop wasting time following up with leads. Let our AI agents do it for you.

Fakhr profil fotoğrafı

Fakhr1 yıl önce

It does more in less time

Benzer Videolar

🚨BREAKING: This Sequoia-backed company just destroyed Devin, OpenAI’s Codex, and Cursor. Factory just launched software agents agents called Droids that write code, close tickets, and deliver docs autonomously. Here’s how it works (with real examples):👇

🚨BREAKING: This Sequoia-backed company just destroyed Devin, OpenAI’s Codex, and Cursor. Factory just launched software agents agents called Droids that write code, close tickets, and deliver docs autonomously. Here’s how it works (with real examples):👇

Hasan Toor

467,738 görüntüleme • 1 yıl önce

The new Factory software AI agents just combined OpenAI’s Codex, Devin, and Cursor into one product. They are fully autonomous agents called Droids that perform deep code research, technical docs, and do autonomous end-to-end coding. Here’s how it works (with real examples)👇:

The new Factory software AI agents just combined OpenAI’s Codex, Devin, and Cursor into one product. They are fully autonomous agents called Droids that perform deep code research, technical docs, and do autonomous end-to-end coding. Here’s how it works (with real examples)👇:

Alvaro Cintas

94,866 görüntüleme • 1 yıl önce

do you understand what just shipped? → AI agents can now design directly on Figma’s canvas. not cheesy mockups… or lame screenshots… real native Figma assets wired to your actual design system → the use_figma MCP tool lets Claude Code, Codex, Cursor, and 6 other coding agents write directly to your Figma files → agents read your component library first and build with what already exists… variables, tokens, auto layout, the works → skills let you teach agents HOW your team designs. a skill is just a markdown file… anyone who understands Figma can write one → also works with Copilot CLI, Copilot in VS Code, Factory, Firebender, Augment, and Warp → free during beta… usage based pricing coming later the design to code gap that’s haunted every product team just collapsed in front of our eyes. designers hand off to agents now no need to wait on developers anymore everyone can take a deep breath now if you’re building products and not connecting Figma to your agents yet, you’re leaving serious speed on the table. set this up today. you’ll thank me later

do you understand what just shipped? → AI agents can now design directly on Figma’s canvas. not cheesy mockups… or lame screenshots… real native Figma assets wired to your actual design system → the use_figma MCP tool lets Claude Code, Codex, Cursor, and 6 other coding agents write directly to your Figma files → agents read your component library first and build with what already exists… variables, tokens, auto layout, the works → skills let you teach agents HOW your team designs. a skill is just a markdown file… anyone who understands Figma can write one → also works with Copilot CLI, Copilot in VS Code, Factory, Firebender, Augment, and Warp → free during beta… usage based pricing coming later the design to code gap that’s haunted every product team just collapsed in front of our eyes. designers hand off to agents now no need to wait on developers anymore everyone can take a deep breath now if you’re building products and not connecting Figma to your agents yet, you’re leaving serious speed on the table. set this up today. you’ll thank me later

klöss

101,073 görüntüleme • 3 ay önce

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 görüntüleme • 1 yıl önce

Just dropped an incredible episode with Matan Grinberg (Matan Grinberg ), founder of Factory Based on what a lot of my friends in Silicon Valley have told me, it's like Devin... but it actually works. ;) In the episode, we built a DocuSign clone in 15 minutes. No joke. It's incredible. 👇 Highlights: 1/ Why Factory stayed stealth for 2 years While Devin got mega hyped, Factory quietly served enterprises, perfecting their "droids" (specialized AI agents) for real-world software development workflows. 2/ The hybrid approach that changes everything Factory runs both locally AND in the cloud. Think: superpowers for you locally, superpowers for your team remotely. OpenAI's Codex promises this eventually - Factory delivers it today. 3/ Live billion-dollar startup demo Watched Matan build a fully functional DocuSign competitor from scratch using natural language. Upload docs, add signatures, email workflows - all working in 15 minutes. 4/ Beyond just coding Factory's "droids" handle the full software lifecycle: planning, PRDs, design docs, coding, testing, maintenance. Most engineers spend <30% of time actually coding - Factory automates the rest. 5/ The future of software development We're moving from "coding in IDEs" to "understanding constraints and delegating to AI." The center of gravity shifts from writing code to planning and testing AI output. 6/ Enterprise-first strategy paying off Started with big companies, now going GA at $40/month. PMs are using it to ship production PRs without bothering engineers. Game-changing for team dynamics. 7/ Watch / listen 🎥 YouTube → 📷 Spotify → 🍎 Apple → 8/ Follow The Team Factory Matan Grinberg Eno Reyes If you build or invest in software, this conversation is your playbook for the next 12 months of AI-powered dev work.

Just dropped an incredible episode with Matan Grinberg (Matan Grinberg ), founder of Factory Based on what a lot of my friends in Silicon Valley have told me, it's like Devin... but it actually works. ;) In the episode, we built a DocuSign clone in 15 minutes. No joke. It's incredible. 👇 Highlights: 1/ Why Factory stayed stealth for 2 years While Devin got mega hyped, Factory quietly served enterprises, perfecting their "droids" (specialized AI agents) for real-world software development workflows. 2/ The hybrid approach that changes everything Factory runs both locally AND in the cloud. Think: superpowers for you locally, superpowers for your team remotely. OpenAI's Codex promises this eventually - Factory delivers it today. 3/ Live billion-dollar startup demo Watched Matan build a fully functional DocuSign competitor from scratch using natural language. Upload docs, add signatures, email workflows - all working in 15 minutes. 4/ Beyond just coding Factory's "droids" handle the full software lifecycle: planning, PRDs, design docs, coding, testing, maintenance. Most engineers spend <30% of time actually coding - Factory automates the rest. 5/ The future of software development We're moving from "coding in IDEs" to "understanding constraints and delegating to AI." The center of gravity shifts from writing code to planning and testing AI output. 6/ Enterprise-first strategy paying off Started with big companies, now going GA at $40/month. PMs are using it to ship production PRs without bothering engineers. Game-changing for team dynamics. 7/ Watch / listen 🎥 YouTube → 📷 Spotify → 🍎 Apple → 8/ Follow The Team Factory Matan Grinberg Eno Reyes If you build or invest in software, this conversation is your playbook for the next 12 months of AI-powered dev work.

Nathan Lands - Lore.com

24,908 görüntüleme • 1 yıl önce

Today we open the Zapier SDK to everyone. If you're building with AI agents, this is for you. I've been using this for 2 months. It's totally changed how I do my job. You install it in your coding agent. Cursor, Claude Code, Codex, whatever you use. Now that agent has access to 8,000+ apps through Zapier and can do anything those APIs can do. I think it’s the most powerful thing we’ve launched in years. Now in open beta. Just give this link right to your agent:

Today we open the Zapier SDK to everyone. If you're building with AI agents, this is for you. I've been using this for 2 months. It's totally changed how I do my job. You install it in your coding agent. Cursor, Claude Code, Codex, whatever you use. Now that agent has access to 8,000+ apps through Zapier and can do anything those APIs can do. I think it’s the most powerful thing we’ve launched in years. Now in open beta. Just give this link right to your agent:

Wade Foster

174,596 görüntüleme • 3 ay önce

🚨We’re excited to Introduce AI HQ — your home for building, activating, and supervising AI agents across your enterprise 🚨 We’re giving IT and business teams an end-to-end platform to co-create AI agents that don’t just assist. They act. These agents are fully integrated, grounded in company data, and built to execute high-impact business processes autonomously. New capabilities in AI HQ include: ⚡ Agent Builder (Beta): Your shared development environment where IT and business teams collaboratively build AI agents. Low-code tools make it easy to map out logic with reusable blocks, connect to systems and data, design interfaces with drag-and-drop simplicity, and more. 🏠 Writer Home: Your personalized AI workspace with 100+ prebuilt agents for every function - from support to sales to HR - ready to go and accessible via desktop, browser, or extensions. It’s your new front door to real AI-powered work. 🛡️ Observability Tools (Beta): Gain full control and visibility into every agent with enterprise-grade observability: monitor activity activity, detect anomalies, and resolve issues before they escalate. It’s how AI moves from experimental to operational. Companies like Uber Commvault and Franklin Templeton (Franklin Templeton) are already using Writer AI agents to reinvent knowledge management, accelerate revenue workflows, and deliver smarter client experiences. This isn’t hype. It’s happening now. 👀 Dive into today’s announcement:

🚨We’re excited to Introduce AI HQ — your home for building, activating, and supervising AI agents across your enterprise 🚨 We’re giving IT and business teams an end-to-end platform to co-create AI agents that don’t just assist. They act. These agents are fully integrated, grounded in company data, and built to execute high-impact business processes autonomously. New capabilities in AI HQ include: ⚡ Agent Builder (Beta): Your shared development environment where IT and business teams collaboratively build AI agents. Low-code tools make it easy to map out logic with reusable blocks, connect to systems and data, design interfaces with drag-and-drop simplicity, and more. 🏠 Writer Home: Your personalized AI workspace with 100+ prebuilt agents for every function - from support to sales to HR - ready to go and accessible via desktop, browser, or extensions. It’s your new front door to real AI-powered work. 🛡️ Observability Tools (Beta): Gain full control and visibility into every agent with enterprise-grade observability: monitor activity activity, detect anomalies, and resolve issues before they escalate. It’s how AI moves from experimental to operational. Companies like Uber Commvault and Franklin Templeton (Franklin Templeton) are already using Writer AI agents to reinvent knowledge management, accelerate revenue workflows, and deliver smarter client experiences. This isn’t hype. It’s happening now. 👀 Dive into today’s announcement:

WRITER

10,835 görüntüleme • 1 yıl önce

Markdown is the new programming language. But writing markdown sucks. So I created a beautiful app to write and edit markdown files with agents, locally. It's called Skribe, an open-source, beautiful markdown editor and you can try it for free today. Just: - Open your codebase - Only markdown files are shown - Edit and write markdown alongside Claude Code or Codex within a beautiful editor

Markdown is the new programming language. But writing markdown sucks. So I created a beautiful app to write and edit markdown files with agents, locally. It's called Skribe, an open-source, beautiful markdown editor and you can try it for free today. Just: - Open your codebase - Only markdown files are shown - Edit and write markdown alongside Claude Code or Codex within a beautiful editor

Chris Ashby

11,258 görüntüleme • 24 gün önce

Sam Altman says soon everyone will be a software engineer and he might be right Sam Altman just casually dropped one of the biggest takes about the future of work and software and people are still sleeping on it. Here’s the core idea, and it’s honestly wild: Natural language is the new syntax You won’t write code. You’ll describe what you want in plain English. Talking to computers becomes the default programming interface. The end of the “army of developers” No product managers writing specs. No giant dev teams for v1. You describe the app and the AI builds it. The overnight app You explain your idea, go to sleep, and the AI spends the night writing, testing, and wiring everything together. You wake up and the product exists. Coffee optional but recommended ☕ Autonomous software agents For complex systems, AI agents live inside the codebase itself. They crawl the repo, fix bugs, write tests, refactor code, and commit changes on their own. A digital workforce that never sleeps Not copilots. Not autocomplete. Actual agents doing ongoing engineering work without supervision. Beyond coding: total company automation Once software is automated, the same logic applies to operations, planning, and even parts of management. Code is just the first domino. If this plays out, “learning to code” becomes less important than learning to think clearly, describe intent, and spot good ideas. Question for you 👀 If everyone can build software, what actually becomes scarce: ideas, taste, or execution?

Sam Altman says soon everyone will be a software engineer and he might be right Sam Altman just casually dropped one of the biggest takes about the future of work and software and people are still sleeping on it. Here’s the core idea, and it’s honestly wild: Natural language is the new syntax You won’t write code. You’ll describe what you want in plain English. Talking to computers becomes the default programming interface. The end of the “army of developers” No product managers writing specs. No giant dev teams for v1. You describe the app and the AI builds it. The overnight app You explain your idea, go to sleep, and the AI spends the night writing, testing, and wiring everything together. You wake up and the product exists. Coffee optional but recommended ☕ Autonomous software agents For complex systems, AI agents live inside the codebase itself. They crawl the repo, fix bugs, write tests, refactor code, and commit changes on their own. A digital workforce that never sleeps Not copilots. Not autocomplete. Actual agents doing ongoing engineering work without supervision. Beyond coding: total company automation Once software is automated, the same logic applies to operations, planning, and even parts of management. Code is just the first domino. If this plays out, “learning to code” becomes less important than learning to think clearly, describe intent, and spot good ideas. Question for you 👀 If everyone can build software, what actually becomes scarce: ideas, taste, or execution?

VraserX e/acc

70,643 görüntüleme • 6 ay önce

Anthropic's Claude team just showed how to give your AI agents real memory in under 18 minutes. Free. From the people who built it. You've been building agents that forget everything between sessions. This fixes that tonight. One person + 10 agents with memory + dreaming = a team that runs 24/7, learns from every task, and improves itself overnight. Worth more than any $500 AI agent course. Bookmark it. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Anthropic's Claude team just showed how to give your AI agents real memory in under 18 minutes. Free. From the people who built it. You've been building agents that forget everything between sessions. This fixes that tonight. One person + 10 agents with memory + dreaming = a team that runs 24/7, learns from every task, and improves itself overnight. Worth more than any $500 AI agent course. Bookmark it. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Himanshu Kumar

11,128 görüntüleme • 2 ay önce

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Kawsar

31,812 görüntüleme • 4 ay önce

Check Run Agents, now available in Macroscope. we made a video to show you how it works! these are super flexible agents you control that let you enforce your team's coding conventions, workflows, and compliance checks during code review. just define in markdown and include trigger rules, model choice/reasoning levels, and tool access (including any 3rd party integrations and MCP servers you've already connected to macroscope)-- then the agent spawns as a Check in GitHub. we've been delighted by the creativity and complexity of what our customers have been doing with check run agents: enforcing style conventions, coordinating multistep db migration workflows, ensuring public-facing docs are updated in sync with code changes, and more.

Check Run Agents, now available in Macroscope. we made a video to show you how it works! these are super flexible agents you control that let you enforce your team's coding conventions, workflows, and compliance checks during code review. just define in markdown and include trigger rules, model choice/reasoning levels, and tool access (including any 3rd party integrations and MCP servers you've already connected to macroscope)-- then the agent spawns as a Check in GitHub. we've been delighted by the creativity and complexity of what our customers have been doing with check run agents: enforcing style conventions, coordinating multistep db migration workflows, ensuring public-facing docs are updated in sync with code changes, and more.

Kayvon Beykpour

66,617 görüntüleme • 2 ay önce

Factory is better than Devin, Codex, and Jules, and it's not even close. This is not just a fully autonomous software engineer but also a product manager and researcher. It's the entire package you need to build a new project or dramatically expand an existing one. I recorded a quick video so you can see how it works. You can use these autonomous Droids from Factory. Here is what they can do: 1. Build a full production-grade app from scratch 2. Develop new features for an existing codebase 3. Migrations or refactors on your codebase 4. Build integrations 5. Generate complete feature specifications 6. Solve and close issues from your issue management system 7. Do deep research on any software topics And Factory can connect to Linear, GitHub, Google Drive, Slack, Jira, Sentry, GitLab, and Notion to do its work. You can use any of the big models to do what you need.

Factory is better than Devin, Codex, and Jules, and it's not even close. This is not just a fully autonomous software engineer but also a product manager and researcher. It's the entire package you need to build a new project or dramatically expand an existing one. I recorded a quick video so you can see how it works. You can use these autonomous Droids from Factory. Here is what they can do: 1. Build a full production-grade app from scratch 2. Develop new features for an existing codebase 3. Migrations or refactors on your codebase 4. Build integrations 5. Generate complete feature specifications 6. Solve and close issues from your issue management system 7. Do deep research on any software topics And Factory can connect to Linear, GitHub, Google Drive, Slack, Jira, Sentry, GitLab, and Notion to do its work. You can use any of the big models to do what you need.

Santiago

70,099 görüntüleme • 1 yıl önce

Introducing the Printing Press, a CLI-factory and a CLI-library. Built with Trevin Chow. 🏭🖨📚 Most APIs suck for agents. Most MCPs suck for agents. Most official CLIs suck for agents. They waste tokens and time. Peter Steinberger 🦞 started making his own because of this. 📚 A Library of agent-native CLIs you install today (Linear, ESPN, Flight GOAT (Google Flights + Kayak nonstop), Contact Goat (LinkedIn + Happenstance + Deepline more) +30+ more) 🏭 A factory that prints new ones for any service - just type /printing-press CLIs are fast, local, SQLite-backed. Work in Claude Code, Codex, OpenClaw, Hermes. 🌐

Introducing the Printing Press, a CLI-factory and a CLI-library. Built with Trevin Chow. 🏭🖨📚 Most APIs suck for agents. Most MCPs suck for agents. Most official CLIs suck for agents. They waste tokens and time. Peter Steinberger 🦞 started making his own because of this. 📚 A Library of agent-native CLIs you install today (Linear, ESPN, Flight GOAT (Google Flights + Kayak nonstop), Contact Goat (LinkedIn + Happenstance + Deepline more) +30+ more) 🏭 A factory that prints new ones for any service - just type /printing-press CLIs are fast, local, SQLite-backed. Work in Claude Code, Codex, OpenClaw, Hermes. 🌐

Matt Van Horn

1,376,820 görüntüleme • 2 ay önce

I built the clipboard I always wanted for working with AI agents. It’s called Bluey and It’s 100% local-first. It lives under your mouse cursor. You can draw on your screen, speak to it, or type what you mean, and Bluey turns all of that into rich context for Claude Code or Codex. I’ve been using it to design websites and debug UI because I can finally say things like “move this here” or “make this section feel cleaner” while pointing at the actual screen. No more writing long explanations. No more manually describing screenshots. No more agents getting lost because they don’t know what “this” or "that" means. You can just point to it, speak or type and it will curate the best possible context for your agents Bluey captures the screenshot, annotation, transcript, app/window context, and the details your agent needs, then sends it directly into your coding session. I am giving it out for free for a while! Im building it with my buddy Omkar Satpute and we would love to hear what you think about it on Discord what context do you wish your agent could understand better?

I built the clipboard I always wanted for working with AI agents. It’s called Bluey and It’s 100% local-first. It lives under your mouse cursor. You can draw on your screen, speak to it, or type what you mean, and Bluey turns all of that into rich context for Claude Code or Codex. I’ve been using it to design websites and debug UI because I can finally say things like “move this here” or “make this section feel cleaner” while pointing at the actual screen. No more writing long explanations. No more manually describing screenshots. No more agents getting lost because they don’t know what “this” or "that" means. You can just point to it, speak or type and it will curate the best possible context for your agents Bluey captures the screenshot, annotation, transcript, app/window context, and the details your agent needs, then sends it directly into your coding session. I am giving it out for free for a while! Im building it with my buddy Omkar Satpute and we would love to hear what you think about it on Discord what context do you wish your agent could understand better?

Milind S

13,302 görüntüleme • 1 ay önce

designing my new personal site with Pencil.dev connected it to Claude Code and turned on "Swarm Mode" and watched agents design my site in real-time, with their cursors actually moving and operating the screen, not just cosmetically! instead of the agents producing a raw HTML file, they generate something called .pen which is just a json file describing all layouts, components, and design. this means that it's easier than ever to have teams collaborate on design exactly as they do on source code (designers and engineers can now speak the same language!) once you are happy with a screen, you can open a new chat and reference .pen frame and start to generate the code (in React/ Next/ Tailwind etc), and run it on your dev server, producing a live website that visually matches your design

designing my new personal site with Pencil.dev connected it to Claude Code and turned on "Swarm Mode" and watched agents design my site in real-time, with their cursors actually moving and operating the screen, not just cosmetically! instead of the agents producing a raw HTML file, they generate something called .pen which is just a json file describing all layouts, components, and design. this means that it's easier than ever to have teams collaborate on design exactly as they do on source code (designers and engineers can now speak the same language!) once you are happy with a screen, you can open a new chat and reference .pen frame and start to generate the code (in React/ Next/ Tailwind etc), and run it on your dev server, producing a live website that visually matches your design

Sandra

93,463 görüntüleme • 4 ay önce

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

124,382 görüntüleme • 1 yıl önce

🤯 Building computer-vision applications is never going to be the same again. As Andrej Karpathy says, "English is going to be the new programming-language", and we just made that happen for programming visual AI. 👨‍💻 This past month, the VLM Run team cooked up something magical that I'm especially proud of - a natural-language interface to build and run computer vision workflows (object-detection, OCR, parsing, and so much more) – all via our new VLM Run MCP server. 🔌 It works with any MCP-compatible AI agent (Claude, OpenAI, Cursor, etc.) and abstracts complex visual workflows into simple English commands. No need to write Python or fiddle with bespoke computer-vision code – just say what you want your agent to do, and it does it. Here’s a glimpse into what you can build today ( ☑️ Image AI agents – run detection, tagging, blurring, cropping, and more traditional CV tasks with English ☑️ Document AI agents – extract totals from invoices, search visual content, or act on what’s found ☑️ Video AI agents – understand scene content, trim clips, add subtitles, and create ready-to-share edits ☑️ And best-of-all, it's fully programmable with English. 🧑‍🍳 MCP Showcase: 📚 MCP Cookbooks: 📚 MCP Docs: #computervision #ai #agents #llm #vlm #mcp #vibecoding #genai

🤯 Building computer-vision applications is never going to be the same again. As Andrej Karpathy says, "English is going to be the new programming-language", and we just made that happen for programming visual AI. 👨‍💻 This past month, the VLM Run team cooked up something magical that I'm especially proud of - a natural-language interface to build and run computer vision workflows (object-detection, OCR, parsing, and so much more) – all via our new VLM Run MCP server. 🔌 It works with any MCP-compatible AI agent (Claude, OpenAI, Cursor, etc.) and abstracts complex visual workflows into simple English commands. No need to write Python or fiddle with bespoke computer-vision code – just say what you want your agent to do, and it does it. Here’s a glimpse into what you can build today ( ☑️ Image AI agents – run detection, tagging, blurring, cropping, and more traditional CV tasks with English ☑️ Document AI agents – extract totals from invoices, search visual content, or act on what’s found ☑️ Video AI agents – understand scene content, trim clips, add subtitles, and create ready-to-share edits ☑️ And best-of-all, it's fully programmable with English. 🧑‍🍳 MCP Showcase: 📚 MCP Cookbooks: 📚 MCP Docs: #computervision #ai #agents #llm #vlm #mcp #vibecoding #genai

Sudeep Pillai

17,789 görüntüleme • 1 yıl önce

"Not a single one of our full-time engineers right now writes code anymore... it's all agentic... the way you build a company completely changes." JD Ross with Joe Lonsdale on the future of software: JD Ross: Not a single one of our full-time engineers right now writes code anymore. They do everything through Codex, Claude Code, or Cursor. Joe Lonsdale: It's all agentic. JD: It's all agentic. Joe: A lot of them are managing lots of agents at once, right? That's how they're working? JD: Yeah, Cole who runs our engineering team has six agents that are running at once at all times just doing different kind of projects. When we create a new ticket in Linear, it automatically kicks off this thing that basically creates a dev environment, which then tries to one shot the solution and then creates a PR that we review. The whole way you build software is changing so quickly. And I think right now the cost of software is just asymptotically dropping to zero... which means that the way you build a company completely changes. We can now have an enterprise customer come up who says, "Oh yeah, this is so close. What we actually need it for is X." We can build X in one day, ship it live, and close that deal. We did this last week... It's a completely different way of even thinking.

"Not a single one of our full-time engineers right now writes code anymore... it's all agentic... the way you build a company completely changes." JD Ross with Joe Lonsdale on the future of software: JD Ross: Not a single one of our full-time engineers right now writes code anymore. They do everything through Codex, Claude Code, or Cursor. Joe Lonsdale: It's all agentic. JD: It's all agentic. Joe: A lot of them are managing lots of agents at once, right? That's how they're working? JD: Yeah, Cole who runs our engineering team has six agents that are running at once at all times just doing different kind of projects. When we create a new ticket in Linear, it automatically kicks off this thing that basically creates a dev environment, which then tries to one shot the solution and then creates a PR that we review. The whole way you build software is changing so quickly. And I think right now the cost of software is just asymptotically dropping to zero... which means that the way you build a company completely changes. We can now have an enterprise customer come up who says, "Oh yeah, this is so close. What we actually need it for is X." We can build X in one day, ship it live, and close that deal. We did this last week... It's a completely different way of even thinking.

American Optimist

21,014 görüntüleme • 4 ay önce

Is Windsurf better than Cursor? impossible to say, but... it does one thing better: soooo... I spent an hour testing windsurf... and this is what i created... and app called "boop-boop" lol... one thing windsurf does is it searches the internet. If you've been watching my videos you know that i go to perplexity all the time to get code examples and docs. but with windsurf you can just say, "search the replicate top image gen models and add them to the chat we just created" It will search the internet, find the right model then write the code. This is great for replicate and openrouter. You can have one api key in your .env file then just tell windsurf to search for docs for [insert ai model] and it will just add it to your app. Impressed tbh.

Is Windsurf better than Cursor? impossible to say, but... it does one thing better: soooo... I spent an hour testing windsurf... and this is what i created... and app called "boop-boop" lol... one thing windsurf does is it searches the internet. If you've been watching my videos you know that i go to perplexity all the time to get code examples and docs. but with windsurf you can just say, "search the replicate top image gen models and add them to the chat we just created" It will search the internet, find the right model then write the code. This is great for replicate and openrouter. You can have one api key in your .env file then just tell windsurf to search for docs for [insert ai model] and it will just add it to your app. Impressed tbh.

Riley Brown

31,043 görüntüleme • 1 yıl önce