正在加载视频...

视频加载失败

返回首页

Next.js devs: don't sleep on agent-browser and the new next-dev-loop skill in 16.3. Here is a demo of using it to fix a super tricky bug in a spreadsheet component. 00:00 Intro 01:52 Demo

bytegrad's profile picture

Wesley

1,772 subscribers

28,208 次观看 • 1 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

1 条评论

Isaac Samuel 的头像
Isaac Samuel1 个月前

This is useful. The new next-dev-loop skill looks powerful for tricky component bugs.

相关视频

Learn "use workflow" in Next.js quickly. Game changer for background jobs, cron jobs, webhooks, etc. 00:00 Intro 01:10 Demo 06:15 "use workflow" 06:43 "use step" 10:19 Sequential vs parallel 10:44 Human-in-the-loop (hook) 13:03 sleep 17:00 Streaming 21:09 Observability
34:40

Learn "use workflow" in Next.js quickly. Game changer for background jobs, cron jobs, webhooks, etc. 00:00 Intro 01:10 Demo 06:15 "use workflow" 06:43 "use step" 10:19 Sequential vs parallel 10:44 Human-in-the-loop (hook) 13:03 sleep 17:00 Streaming 21:09 Observability

Wesley

16,001 次观看 • 10 个月前

Give your AI agent a wallet on Base 00:00 intro 00:15 bankrbot 00:43 Coinbase Developer Platform🛡️ agent wallets 01:10 demo of my agent 02:00 how bankrbot wallet works 02:24 how Coinbase Developer Platform🛡️ wallets work 02:51 open-wallet skill by Stephan 03:20 requesting a spend permission
5:45

Give your AI agent a wallet on Base 00:00 intro 00:15 bankrbot 00:43 Coinbase Developer Platform🛡️ agent wallets 01:10 demo of my agent 02:00 how bankrbot wallet works 02:24 how Coinbase Developer Platform🛡️ wallets work 02:51 open-wallet skill by Stephan 03:20 requesting a spend permission

Youssef

43,332 次观看 • 7 个月前

Testing Hermes with a wallet on Base 00:00 intro 01:00 setup and skills 02:40 spinning a wallet using Coinbase Developer Platform🛡️ 04:05 doing a swap 05:40 using in-built base skill 07:04 skills to build on base
9:27

Testing Hermes with a wallet on Base 00:00 intro 01:00 setup and skills 02:40 spinning a wallet using Coinbase Developer Platform🛡️ 04:05 doing a swap 05:40 using in-built base skill 07:04 skills to build on base

Youssef

17,471 次观看 • 6 个月前

Introducing the new dev-browser cli. The fastest way for an agent to use a browser is to let it write code. Just `npm i -g dev-browser` and tell your agent to "use dev-browser"
0:30

Introducing the new dev-browser cli. The fastest way for an agent to use a browser is to let it write code. Just `npm i -g dev-browser` and tell your agent to "use dev-browser"

Sawyer Hood

870,294 次观看 • 5 个月前

It has been a long time since I made a video. I am sharing a deep dive into 2fac, a new 2FA app I built to replace Authy. What makes this project special is its massive scope, running natively across Android, iOS, watchOS, desktop, CLI, browser extensions, and the web. Building this many features across so many platforms was only possible through agentic coding. Huge thanks to Copilot, Claude, OpenCode, and Pi for completely changing how I write software. Here is what is covered in the video. In the pre-AI world, so many features, taking it to such a polished state (ui, design, relialibility of how it works, and quality of code too, you can take a look for yourelf) single handedly, that too working on spare time on the side from a day job, was simply not possible for non 10x, mid engineers like me 00:00:00 Project Overview & Motivation 00:03:31 Android App Demo 00:04:19 iOS & watchOS App Demo 00:05:32 Desktop App Demo 00:06:05 System Tray Integration 00:07:05 CLI Demo 00:08:44 Browser Extension Demo 00:10:00 Web App (PWA) Demo 00:11:40 Secure Unlock & Passkeys 00:16:30 GitHub Repo & Release Plans 00:17:30 CI/CD Pipeline Setup 00:19:00 AI Agentic Coding Workflow 00:23:50 Production Usage Warning 00:26:00 Custom AI Agent Skills 00:28:30 Automated Planning & Roadmaps 00:31:14 UI Testing with Maestro 00:35:12 Creating Custom AI Agents 00:38:34 Codebase Test Coverage 00:41:30 AI-Driven TDD
43:11

It has been a long time since I made a video. I am sharing a deep dive into 2fac, a new 2FA app I built to replace Authy. What makes this project special is its massive scope, running natively across Android, iOS, watchOS, desktop, CLI, browser extensions, and the web. Building this many features across so many platforms was only possible through agentic coding. Huge thanks to Copilot, Claude, OpenCode, and Pi for completely changing how I write software. Here is what is covered in the video. In the pre-AI world, so many features, taking it to such a polished state (ui, design, relialibility of how it works, and quality of code too, you can take a look for yourelf) single handedly, that too working on spare time on the side from a day job, was simply not possible for non 10x, mid engineers like me 00:00:00 Project Overview & Motivation 00:03:31 Android App Demo 00:04:19 iOS & watchOS App Demo 00:05:32 Desktop App Demo 00:06:05 System Tray Integration 00:07:05 CLI Demo 00:08:44 Browser Extension Demo 00:10:00 Web App (PWA) Demo 00:11:40 Secure Unlock & Passkeys 00:16:30 GitHub Repo & Release Plans 00:17:30 CI/CD Pipeline Setup 00:19:00 AI Agentic Coding Workflow 00:23:50 Production Usage Warning 00:26:00 Custom AI Agent Skills 00:28:30 Automated Planning & Roadmaps 00:31:14 UI Testing with Maestro 00:35:12 Creating Custom AI Agents 00:38:34 Codebase Test Coverage 00:41:30 AI-Driven TDD

Arnav Gupta

109,905 次观看 • 6 个月前

FULL JEV TUTORIAL: HOW TO BUILD WITH IT AND UNLOCK NEW AI APPLICATIONS. → 0:00 Intro → 0:34 What is Jev → 4:06 API setup → 5:59 Demo 1: Voice-controlled browser → 11:33 Demo 2: AI memory → 17:27 Demo 3: YouTube predictor
22:41

Sensitive content

FULL JEV TUTORIAL: HOW TO BUILD WITH IT AND UNLOCK NEW AI APPLICATIONS. → 0:00 Intro → 0:34 What is Jev → 4:06 API setup → 5:59 Demo 1: Voice-controlled browser → 11:33 Demo 2: AI memory → 17:27 Demo 3: YouTube predictor

0xMarioNawfal

38,569 次观看 • 5 小时前

For over a year, Jeremy Howard has been in stealth mode. In this exclusive talk, he showcases what he's been working on. He & Jonathan Whitaker show us SolveIt, a new dev environment and programming paradigm. 🤯 Imagine this workflow: - Build a web app & interact with its UI on the same screen as your code. No more flipping to a separate browser. - Use live variables from your REPL directly in prompts to the AI. The AI knows your current state. - Turn any Python function into an AI tool instantly. No no registering tools or MCP. Just write a function in a cell and tell the AI to use it. This is a live, malleable environment that fuses the best ideas from Literate Programming (Knuth), the live-object world of Smalltalk, and the interactive cells of Jupyter. Who is Solveit for? Jeremy's take: SolveIt is best for programmers who are either very new ( 20 years). Why? Because developers in the middle (3-20 years) often have ingrained workflows and can find this different paradigm confronting. New devs are open-minded and build good habits from scratch, while veterans immediately recognize how this approach solves decades-old problems of complexity and state management. My Thoughts It's early days, but it is super cool. You get all the fun of trying a new programming language without learning new syntax (Python), because it will show you new patterns and ways of doing this. If you are wiling to climb the learning curve it is an extremely powerful tool that you can be productive with on real tasks like writing and coding. I'm personally addicted to it for several workflows and am afraid of losing it tbh. How Can You Try It? Just follow Jeremy Howard - he will announce something in the coming weeks or months (I suspect if this post is popular he might do something soon 🤣 ) TIMESTAMPS (00:00:00) - Introduction (00:00:30) - The SolveIt Method vs. "Vibe Coding" (00:04:00) - Investing in Yourself: Long-Term Skill Building (00:07:45) - Software Engineering vs. Short-Term Gains (00:12:15) - The Problem-Solving Loop: Understand, Plan, Implement, Review (00:18:50) - Example: Literate Programming with the Claudette Library (00:24:15) - First Look at the SolveIt Environment (00:28:34) - Demo Start: Building an Eval for Multimodal Models (00:31:16) - Iterative Development: Exploring the iNaturalist API (00:39:15) - Catching Bugs Instantly by Working Step-by-Step (00:43:37) - Prompting LLMs with Structured Outputs (00:51:54) - Demo: Building a Live Web App Inside SolveIt with FastHTML (01:00:24) - Demo: Exploring a Complex API (Cloudflare) (01:08:45) - Creating Custom AI Agent Tools with Zero Boilerplate (01:19:00) - SolveIt Ergonomics: Modes, Secrets, and Keyboard Shortcuts (01:28:30) - The Power of the SolveIt Community (01:30:45) - Who Should Use SolveIt? (01:34:30) - This is Just the Tip of the Iceberg YT Video and links in reply
1:36:14

For over a year, Jeremy Howard has been in stealth mode. In this exclusive talk, he showcases what he's been working on. He & Jonathan Whitaker show us SolveIt, a new dev environment and programming paradigm. 🤯 Imagine this workflow: - Build a web app & interact with its UI on the same screen as your code. No more flipping to a separate browser. - Use live variables from your REPL directly in prompts to the AI. The AI knows your current state. - Turn any Python function into an AI tool instantly. No no registering tools or MCP. Just write a function in a cell and tell the AI to use it. This is a live, malleable environment that fuses the best ideas from Literate Programming (Knuth), the live-object world of Smalltalk, and the interactive cells of Jupyter. Who is Solveit for? Jeremy's take: SolveIt is best for programmers who are either very new ( 20 years). Why? Because developers in the middle (3-20 years) often have ingrained workflows and can find this different paradigm confronting. New devs are open-minded and build good habits from scratch, while veterans immediately recognize how this approach solves decades-old problems of complexity and state management. My Thoughts It's early days, but it is super cool. You get all the fun of trying a new programming language without learning new syntax (Python), because it will show you new patterns and ways of doing this. If you are wiling to climb the learning curve it is an extremely powerful tool that you can be productive with on real tasks like writing and coding. I'm personally addicted to it for several workflows and am afraid of losing it tbh. How Can You Try It? Just follow Jeremy Howard - he will announce something in the coming weeks or months (I suspect if this post is popular he might do something soon 🤣 ) TIMESTAMPS (00:00:00) - Introduction (00:00:30) - The SolveIt Method vs. "Vibe Coding" (00:04:00) - Investing in Yourself: Long-Term Skill Building (00:07:45) - Software Engineering vs. Short-Term Gains (00:12:15) - The Problem-Solving Loop: Understand, Plan, Implement, Review (00:18:50) - Example: Literate Programming with the Claudette Library (00:24:15) - First Look at the SolveIt Environment (00:28:34) - Demo Start: Building an Eval for Multimodal Models (00:31:16) - Iterative Development: Exploring the iNaturalist API (00:39:15) - Catching Bugs Instantly by Working Step-by-Step (00:43:37) - Prompting LLMs with Structured Outputs (00:51:54) - Demo: Building a Live Web App Inside SolveIt with FastHTML (01:00:24) - Demo: Exploring a Complex API (Cloudflare) (01:08:45) - Creating Custom AI Agent Tools with Zero Boilerplate (01:19:00) - SolveIt Ergonomics: Modes, Secrets, and Keyboard Shortcuts (01:28:30) - The Power of the SolveIt Community (01:30:45) - Who Should Use SolveIt? (01:34:30) - This is Just the Tip of the Iceberg YT Video and links in reply

Hamel Husain

111,916 次观看 • 1 年前

Sound on for this one. We wired up OpenAI's new STT and TTS models into a single voice agent. The results are super fun! Link to a live demo in the next tweet.
0:29

Sound on for this one. We wired up OpenAI's new STT and TTS models into a single voice agent. The results are super fun! Link to a live demo in the next tweet.

dsa

32,310 次观看 • 1 年前

Coding agents suck at using a browser. Playwright MCP burns through your context window before you even send your first prompt. That is why I built Dev Browser, a Claude Skill to let your agent close the loop without eating up tokens.
0:45

Coding agents suck at using a browser. Playwright MCP burns through your context window before you even send your first prompt. That is why I built Dev Browser, a Claude Skill to let your agent close the loop without eating up tokens.

Sawyer Hood

312,803 次观看 • 9 个月前

hyperspace: auto-recompute every dependent agent based on changes to it’s predecessors, just like cells of a spreadsheet formula this is the fundamental new UI, ps: an old demo from July 15th shown at The Agentic Browser Summit. do you want a sneak peek of the updated one ?
1:28

hyperspace: auto-recompute every dependent agent based on changes to it’s predecessors, just like cells of a spreadsheet formula this is the fundamental new UI, ps: an old demo from July 15th shown at The Agentic Browser Summit. do you want a sneak peek of the updated one ?

Varun

92,012 次观看 • 1 年前

Here's a showcase of the new ED added: Malzeno in #MHNow ! Malzeno is peak, and as usual, Now just adapted it wonderfully 😳 Thanks as always to Niantic for providing me access to the content 🙏 00:00 - Intro 00:15 - Lance Gameplay 01:58 - LBG Gameplay
4:01

Here's a showcase of the new ED added: Malzeno in #MHNow ! Malzeno is peak, and as usual, Now just adapted it wonderfully 😳 Thanks as always to Niantic for providing me access to the content 🙏 00:00 - Intro 00:15 - Lance Gameplay 01:58 - LBG Gameplay

Shincry

12,773 次观看 • 10 个月前

I heard it's a tough market... 🤔 ... so I built an agent that finds you the hottest job offers for you using Spend Permissions + Exa + x402. Exa has the type of results you won't find with a simple google search. 00:00 intro 00:40 demo (base app) 03:40 code Links 👇
4:21

I heard it's a tough market... 🤔 ... so I built an agent that finds you the hottest job offers for you using Spend Permissions + Exa + x402. Exa has the type of results you won't find with a simple google search. 00:00 intro 00:40 demo (base app) 03:40 code Links 👇

Youssef

11,703 次观看 • 5 个月前

A deep dive on the Claude Agent SDK - everything you need to know about deployment 00:00 Intro 01:08 The agent loop 03:23 Core primitives 05:30 Tools vs MCP vs skills 07:08 Context windows 10:47 Building on Replit 15:17 Creating a Todoist agent 22:06 Debugging 28:23 Deployment
30:44

A deep dive on the Claude Agent SDK - everything you need to know about deployment 00:00 Intro 01:08 The agent loop 03:23 Core primitives 05:30 Tools vs MCP vs skills 07:08 Context windows 10:47 Building on Replit 15:17 Creating a Todoist agent 22:06 Debugging 28:23 Deployment

matt palmer

29,402 次观看 • 7 个月前

WebMCP is a game changer for browser agents I built a skill that adds WebMCP support to any codebase - in this demo, I turned Excalidraw into an agent-native experience in a few minutes then I used Stagehand to control the canvas and draw anything. works on any open-source codebase
0:37

WebMCP is a game changer for browser agents I built a skill that adds WebMCP support to any codebase - in this demo, I turned Excalidraw into an agent-native experience in a few minutes then I used Stagehand to control the canvas and draw anything. works on any open-source codebase

Shrey Pandya

13,785 次观看 • 16 天前

A demo of the animations[.]dev skill file using Claude Code. It can review your animations, suggest improvements, and basically answer all your motion-related questions based on my experience gathered over the years.
0:36

A demo of the animations[.]dev skill file using Claude Code. It can review your animations, suggest improvements, and basically answer all your motion-related questions based on my experience gathered over the years.

Emil Kowalski

124,681 次观看 • 8 个月前