Latest YouTube Videos

Checkout https://agenticjumpstart.com to learn more tips and tricks for vibe and agentic coding

I Built an App Which Manages my Projects

Buy the course now: https://agenticjumpstart.com Join the Agentic Jumpstart community: https://discord.gg/JUDWZDN3VT --------- Have a video suggestion? Post it here: https://suggestions.webdevcody.com/ My Game https://survivethenightgame.com/ My Courses 🤖 https://agenticjumpstart.com ⚛️ https://beginner-react-challenges.webdevcody.com Useful Links 💬 Discord: https://discord.gg/N2uEyp7Rfu 🔔 Newsletter: https://newsletter.webdevcody.com/ 📁 GitHub: https://github.com/webdevcody 📺 Twitch: https://www.twitch.tv/webdevcody 🤖 Website: https://webdevcody.com

Live content collections (first look)

Astro 6 is getting close. One of it's major features, live content collections, requires exploration. Here's a quick first look at what's coming. 🔗 Key Links 🔗 - Github: https://github.com/coding-in-public/live-content-collections-first-look --------------------------------------- 🔗 Additional Links 🔗 Preview links - https://deploy-preview-12604--astro-docs-2.netlify.app/en/reference/content-loader-reference/#building-a-live-loader - https://deploy-preview-12604--astro-docs-2.netlify.app/en/guides/content-collections/#live-content-collections --------------------------------------- 📹 Related Videos 📹 - https://youtu.be/DbPc6YP-oR4 --------------------------------------- 🌐 Connect With Me 🌐 - Astro course: https://learnastro.dev - Website: https://codinginpublic.dev - Blog: https://chrispennington.blog 🤝 Follow Me 🤝 - Twitter: https://twitter.com/cpenned - BlueSky: https://bsky.app/profile/codinginpublic.dev 💸 Support Me 💸 - Patreon: https://www.patreon.com/coding_in_public - Buy Me a Coffee: https://www.buymeacoffee.com/chrispennington

The Easiest Contact Form With Next.js 16 (Server Actions + DB + Tests)

Build the easiest Contact Form with Next.js 16, complete with Server Actions, a Neon database, Drizzle ORM, Shadcn UI, and even automatic tests using an awesome testing tool TestSprite. Check it out 👉 https://www.testsprite.com/?via=orcdev This is a perfect practical mini-project if you want to understand: ✅ How to use Server Actions properly ✅ How to pass data from a form to your backend ✅ How to save submissions in a real database ✅ How to write simple automated tests ✅ How to structure a clean, reusable Next.js project The entire project is open source, grab the repo and try it yourself! https://github.com/TheOrcDev/simple-contact-form Make sure to check 8bitcn! https://www.8bitcn.com/ If you're looking for custom web solutions to elevate your business, we've got you covered! 👉 Visit us at: https://www.hordewebsolutions.com/ Next video to watch: https://youtu.be/lG_mTu0wyZA ⚔️ Join The Horde - Discord: https://discord.com/invite/uFB5YzH9YG - Github: https://github.com/TheOrcDev - X: https://x.com/theorcdev Some of the projects to check: Dashboard: https://github.com/TheOrcDev/orcish-dashboard AI Framework: https://github.com/TheOrcDev/orcish-ai-nextjs-framework My first SaaS project, register and get 5 free tokens! https://www.textualgames.com/ 00:00 Intro 00:29 Initializing Next.js 01:18 Setting Up Shadcn 03:56 Building the Contact Form 09:57 Starting the Test Setup 10:28 Implementing the Database & Drizzle ORM 14:10 Writing the Server Actions 17:03 Final Automated Tests Completed #webdevelopment #orcdev #react #nextjs #typescript

How to Get Claude Opus 4.5 FREE for Coding

🚀 Discover how to access Opus 4.5, the most intelligent "artificial intelligence" model, for free. This guide shows you exactly "how to code" using "claude opus coding" and helps you determine if it's the "best coding ai" for your projects. Start your "ai programming" journey without any cost and see its power today.

I built a b2b voice ai agent app

In this video, I build an AI voice agent that can place and receive calls. I show you the tools I use, how I built it, and share some code you can play with. Resources: Voice Agent server: https://rasmic.link/voice-agent Vapi AI: https://rasmic.link/vapi My Links: 🌐 My Site: https://rasmic.link/site 🏭 My product studio: https://rasmic.link/fabrika ⚡ Nextjs Starter Kit: https://rasmic.link/next-starter ⚛️ React Starter kit: https://rasmic.link/react-starter Socials: 🐦 Follow me on X: https://rasmic.link/x 💬 Join my Discord: https://rasmic.link/discord ▶️ Subscribe to my second channel: https://rasmic.link/more-micky Tools I use: 🌐 Framer (use RASMIC for 2 months free of Framer Pro): https://rasmic.link/framer 📚 Programming courses: https://rasmic.link/scrimba 📸 My Camera: https://rasmic.link/camera 📺 Screen Recording Software: https://rasmic.link/screen-studio

Opus 4.5 and GPT 5.1 Codex Max in Droid

Most AI coding tools break at 50% context window. Droid from Factory AI handles 6-10 million tokens per session without losing track of the spec. Today I'm migrating https://RayTranscribes.com to Vercel AI SDK v5 using Droid with Opus 4.5 and ChatGPT 5.1 Codex Max. Real production code, real multi-provider setup (Grok, Deepgram, Assembly AI, OpenAI). I'll also show Cursor Agent on some tasks so you can see the workflow differences. This is a chill code stream - just hanging out and shipping features end-to-end. Drop questions in chat, bring your own project if you want to code along. Picking up from the plan we built last stream: https://youtube.com/live/oAJMtessB4I?feature=share Tools used: - Droid (Factory AI) - Claude Opus 4.5 - ChatGPT 5.1 Codex Max - Cursor - Convex - Vercel AI SDK v5 - Vercel Blobstore Discord: https://rfer.me/discord Wispr Flow: https://rfer.me/wispr Timestamps 00:00:00 Introducing Opus 4.5 and other new AI models 00:00:45 Recapping the Cursor vs. Droid planning comparison 00:01:20 Today's goal: Migrating RayTranscribe to AISDK V5 00:02:26 Demoing RayTranscribe's new features and speed 00:05:41 Answering Droid's open questions from the initial plan 00:11:15 Explaining and cleaning up Git work trees 00:14:56 Emphasizing the importance of planning with AI agents 00:17:59 Reviewing the comprehensive migration plan from Droid 00:22:54 Pro-tip: Backing up the Convex database before coding 00:28:04 Explaining why Droid's Opus 4.5 output is better 00:34:26 The origin story of the RayTranscribes app 00:40:47 Agent refactors code using AISDK's built-in error handling 00:48:48 Agent discovers a bug in the AISDK and creates a workaround 00:56:18 Adding a format version to the schema for future-proofing 01:05:09 Why Anthropic acquiring Bun is a huge strategic move 01:17:02 Recapping the collab with Cole Medin on Linear integration 01:23:24 Verifying AISDK V5's standard error handling 01:30:28 Announcing the StartMy.ai project and local meetups 01:38:00 Implementing dictionary keyword support for transcription 01:45:22 Wrapping up and planning for the next stream

I Let Claude Code Build an App for 24 Hours

Buy the course now: https://agenticjumpstart.com course. Join the Agentic Jumpstart community: https://discord.gg/JUDWZDN3VT article: https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents anthropics repo: https://github.com/anthropics/claude-quickstarts/tree/main/autonomous-coding --------- Have a video suggestion? Post it here: https://suggestions.webdevcody.com/ My Game https://survivethenightgame.com/ My Courses 🤖 https://agenticjumpstart.com ⚛️ https://beginner-react-challenges.webdevcody.com Useful Links 💬 Discord: https://discord.gg/N2uEyp7Rfu 🔔 Newsletter: https://newsletter.webdevcody.com/ 📁 GitHub: https://github.com/webdevcody 📺 Twitch: https://www.twitch.tv/webdevcody 🤖 Website: https://webdevcody.com

Claude, ChatGPT, Gemini in ONE Place? Here's How VibeProxy Makes It Happen

Learn how to route your existing Claude Pro, OpenAI, and Gemini Advanced subscriptions directly into your favorite AI coding environments. Whether you are automating tasks with Factory AI Droids, managing agents in Google’s new Antigravity IDE, or coding in Zed and Amp Code, this workflow will save you money while giving you access to the most powerful models available. https://www.bitdoze.com/vibeproxy-ai-subscriptions-guide/

Why I stopped wearing my Apple Watch as an Ex-Apple Engineer

Claude SDK: 24-Hour Coding Agent | Cole Medin

Cole Medin walks us through Anthropic's harness for long-running agents and shows what happens when you let Claude code for 24 hours straight. We built on top of the official Claude Agent SDK quickstart and added Linear for task management and observability. The core problem this solves: agents lose all memory between context windows. The harness uses two specialized agents - an initializer that sets up the environment and creates tasks, and a coding agent that makes incremental progress while leaving clean artifacts for the next session. Cole showcases a Claude.ai clone that was built entirely by this system running autonomously. Repo: https://github.com/coleam00/Linear-Coding-Agent-Harness Timestamps: 00:00:00 Introduction to the live stream and guest Ray. 00:00:59 Explaining the main topic: Anthropic's harness for long-running agents. 00:03:32 Ray introduces himself and his AI coding background. 00:08:13 Explaining the core problem: agents and long context windows. 00:10:30 Why Cole integrated Linear for task management and observability. 00:13:42 Discussing Archon, Cole's open-source AI command center. 00:21:55 Architectural deep dive: How the agent harness works. 00:25:50 Showing the detailed `app_spec.md` file for building a Claude.ai clone. 00:30:52 Pro-tip: How to use a Claude Max subscription instead of API credits. 00:39:20 Showcase: A Claude.ai clone built by the harness in 24 hours. 00:46:57 Detailing the prompt changes for the Linear integration. 00:49:02 Ray's 'AGI' moment seeing the fully integrated system. 00:50:58 Explaining the Test-Driven Development (TDD) approach used. 01:04:18 Kicking off the live demo. 01:09:21 Live demo: The initializer agent creates tasks in Linear. 01:14:35 Live demo: Agent uses Puppeteer to validate the app. 01:22:30 How to adapt the harness for other models (Codex, OpenCode). 01:27:36 Live demo: The agent builds the initial UI layout. 01:34:50 A fun detour into cooking and favorite pizza. 01:41:09 Will AI stop the creation of new programming languages? 01:50:08 The importance of automated testing in AI workflows. 01:56:48 Ray provides a complete summary of the harness architecture. 01:59:04 Cole discusses his Dynamous community and coding course. 02:04:50 Final thoughts and wrap-up. Resources: Anthropic Engineering Article: https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents Claude Agent SDK Quickstart: https://github.com/anthropics/claude-quickstarts/tree/main/autonomous-coding Cole's Channel: https://www.youtube.com/@ColeMedin Dynamis Community: https://dynamous.ai The harness and principles here are tool-agnostic. You could swap Claude for Codex, Linear for JIRA, and the architecture still applies.

Cursor, Droid, Claude: Why Your Agent Forgets Rules

Your AI agent follows instructions for a while, then just does its own thing. Whether you're using Cursor, Droid, Claude Code, Codex, or GPT-5.1 - I've been there with all of them. In this video, I show you my actual AGENTS.md files, the exact prompt I use to generate them, and why this structure lets me run sessions that are millions of tokens long without the agent going off the rails. The secret is just-in-time context indexing. Instead of one massive file drowning the context window, the agent pulls what it needs when it needs it. Works with Cursor rules, CLAUDE.md files, and any agent that reads markdown instructions. GET THE TOOLS - My generate-AGENTS.md Prompt: https://rfer.me/agentsmd - My generate-CLAUDE.md Prompt: https://rfer.me/claudemd - Try Droid (40M Free Tokens): https://rfer.me/rayfactory - Join our Discord (FREE MONTH w/ code COOKWITHME): https://rfer.me/discord Timestamps 00:00 Why AI agents ignore your instructions 00:38 Example: Cursor fails to rename a file correctly 01:53 Introducing the AGENTS.md file structure 02:34 Explaining the hierarchical repo structure 03:26 How just-in-time context indexing works 03:47 The prompt that generates AGENTS.md files 04:00 The five core principles for the agent to follow 05:03 How to run the generation prompt on your codebase 06:33 Comparing AGENTS.md with CLAUDE.md 07:07 Why multi-million token sessions don't fail 08:05 Three key takeaways to improve your AI agent CONNECT WITH RAY X (Twitter): https://x.com/RayFernando1337 - 1-1 AI Shipping Mentorship (December): https://startmy.ai #Cursor #ClaudeCode #Droid #GPT5 #Codex #Opus45 #AIcoding #CursorRules #FactoryAI #SoftwareEngineering #AgenticWorkflow