AI Built Our ENTIRE Elixir App in 2 Hours (ft. Claude Code + Tidewave)

Claude Code Tutorial: Beginner to Advanced in 20 Minutes. Join our FREE community with free prompts & guides: https://www.skool.com/ai-launchpad/about Chapters: 0:00 - Intro 1:10 - What is Claude & Setup 3:54 - Plan mode & prompting 6:18 - First results & Iteration 8:18 - Claude.md & MCP 12:12 - Context management & extended thinking 16:10 - Deploy your builds 17:07 - Skills & Hooks & Routines 18:39 - Outro For business inquiries including sponsorships and collaborations, please email: business@zinhomedia.com

An overview and starting point for Claude Code. Check out my coding with AI course: https://www.codingwithaicourse.com/ Get the Neon free plan: https://get.neon.com/6uuwMG3 Follow Neon to not miss course giveaways: - X/Twitter: https://x.com/neondatabase - Linkedin: https://www.linkedin.com/company/neondatabase Github Gist With Prompts: https://gist.github.com/bradtraversy/9937e0ecfc8a5b269ce6a885636670dc Crypto Dash Repo: https://github.com/bradtraversy/crypto-dash Timestamps: 0:00 - intro 2:23 - What Is Claude Code 3:56 - Installing Claude 6:43 - First Launch 7:26 - Models & Usage Limits 10:44 - Effort 11:14 - Using Claude In VS Code 12:16 - The First Prompt 16:10 - Shell Mode 17:30 - Modes 19:15 - Settings & Permissions 22:55 - VS Code Extension 24:05 - Refactoring Code 27:03 - Context, Tokens & Clearing 29:20 - Global Sessions 33:14 - Working on an Existing Project 35:48 - Claude.md File & /init 39:28 - Plan Mode 44:58 - Adding Favorites Feature 48:05 - Skills 53:27 - MCPs 57:51 - Sub-Agents

Learn to use Anthropic's Claude Agent SDK (formerly Claude Code SDK) for AI-powered development workflows! https://platform.claude.com/docs/en/agent-sdk/overview https://x.com/trq212 **AI Summary** This workshop by Thariq Shihipar (Anthropic) details the architecture and implementation of the **Claude Agent SDK**. The session moves from high-level theory—defining "agents" as autonomous systems that manage their own context and trajectory—to a live-coding demonstration. Shihipar builds an agent "Harness" from scratch, implementing the core **Agent Loop** (Context Thought Action Observation), integrating the **Bash tool** for general computer use, and demonstrating **Context Engineering** via the file system to maintain state across long tasks. **Timestamps** 00:00 Introduction: Agenda and the "Agent" definition 05:15 The "Harness" concept: Tools, Prompts, and Skills 10:10 Live Coding Setup: Initializing the Agent class and environment 15:45 implementing the "Think" step: Getting the model to reason before acting 25:20 The Agent Loop: connecting `act`, `observe`, and `loop` 33:10 Tool Execution: Handling XML parsing and tool inputs 42:00 The "Bash" Tool: Giving the agent command line access 49:30 Safety & Permissions: "ReadOnly" vs "ReadWrite" file access 58:15 Context Engineering: Using `ls` and `cat` to build dynamic context 01:05:00 The "Monitor": Viewing the agent's thought process in real-time 01:12:45 Handling "Stuck" States: Feedback loops and error correction 01:21:20 Multi-turn Complex Tasks: Building a "Research Agent" demo 01:35:10 Refactoring patterns: "Hooks" and deterministic overrides 01:48:39 Q&A: Reproducibility, helper scripts, and non-determinism 01:50:31 Q&A: Strategies for massive codebases (50M+ lines) 01:52:00 Closing remarks and future SDK roadmap * **Evolution of AI Capabilities:** Shihipar argues we are shifting from **LLM Features** (categorization, single turn) to **Workflows** (structured, multi-step chains like RAG) to **Agents**. He defines agents as systems that *"build their own context, decide their own trajectories, and work very autonomously"* rather than following a rigid pipeline. * **The Claude Agent SDK Architecture:** The SDK is built directly on top of **Claude Code** because Anthropic found they were *"rebuilding the same parts over and over again"* for internal tools. * **The Harness:** A robust agent requires more than just a model; it needs a "Harness" containing Tools, Prompts, a **File System**, Skills, Sub-agents, and Memory. * **Opinionated Design:** The SDK bakes in lessons from deploying Claude Code, specifically the "opinion" that general computer use (Bash) is often superior to bespoke tools. * **The Power of the Bash Tool:** A key technical insight is that the **Bash tool** is often the most powerful tool for an agent. Instead of building custom tools for every action (e.g., a specific API wrapper for a file conversion), giving the agent access to the shell allows it to use existing software (like `ffmpeg`, `grep`, or `git`) to solve problems flexibly, similar to how a human developer works. * **Context Engineering:** Shihipar introduces the concept of **Context Engineering** via the file system. Instead of just "Prompt Engineering," the agent uses the file system to manage its state and context. * **Files as Memory:** The agent can write to files to "remember" things or create its own documentation (e.g., `CLAUDE.md`) to ground future actions. * **Verification:** The file system serves as a ground truth for the agent to verify its work (e.g., checking if a file was actually created). * **The Agent Loop & Intuition:** Building a successful agent loop is described as *"kind of an art or intuition"*. The loop generally follows a **Gather Context Take Action Verify Work** cycle. Shihipar emphasizes that this loop allows the agent to self-correct, a capability missing from rigid workflows. * **Strategies for Determinism (Hooks):** During the Q&A, a technique for controlling agent behavior is discussed: **Hooks**. * If an agent hallucinates or skips a step (e.g., guessing a Pokemon stat instead of checking a script), a hook can intercept the response and inject feedback: *"Please make sure you write a script, please make sure you read this data."* * This enforces rules like "read before you write" without retraining the model. * **Scaling to Large Codebases:** For massive codebases (50M+ lines), standard tools like `grep` or basic context window stuffing fail. * **Semantic Search Limitations:** Shihipar notes that while semantic search is a common solution, it is *"brittle"* because the model isn't trained on the specific semantic index. * **Solution:** He recommends good **"Claude MD"** files (context files) and starting the agent in a specific subdirectory to limit scope, rather than trying to index the entire 50M lines at once.

Welcome to our Elixir full course, 'Phoenix LiveView: Building a GitHub Gist Clone'! Jacob Luetzow, your Elixir Mentor, will lead you through creating a GitHub Gist clone with Phoenix LiveView. Starting from the basics of setting up a Phoenix LiveView app, we'll cover essential topics like user authentication, form validation, database interactions, and designing an engaging user interface. We're not stopping there; we'll dive into enhancing our app's look and feel with Tailwind CSS and JavaScript. Each tutorial in this series is designed to build upon the previous, offering a comprehensive step-by-step guide to tackle real-world Elixir programming challenges. Whether you're just starting or are an experienced developer keen to broaden your Elixir knowledge, this series has something for everyone. Ready to start building sophisticated web applications with Phoenix LiveView? Press play, and let's begin this educational adventure together!

💰 Mentorship to six figure software engineer - https://calcur.tech/mentorship ⚙️ Backend Engineering Mind Map - https://calcur.tech/mindmap 💻 System Design Playlist - https://calcur.tech/system-design Elixir Programming Introduction - https://youtu.be/-lgtb-YSUWE Timestamps: 00:00:00 - Intro 00:01:20 - What is Elixir Phoenix 00:03:38 - MVC Pattern 00:05:49 - Installation 00:08:25 - Project Structure 00:10:03 - Main files 00:11:08 - Other Folders 00:12:12 - Create a Repo 00:13:59 - Basic Application Architecture 00:16:12 - Adding a New Page with Mock Data 00:22:24 - Creating an API 00:22:49 - Working with the Database 00:31:53 - Routes 00:32:48 - Updating a Resource 00:34:45 - Delete 00:35:23 - Users and Relationships 00:36:01 - Update the Model 00:37:23 - Making the association in models 00:40:25 - Nested Data in API Calls 00:43:17 - Get a User’s Posts 00:48:21 - Conclusion 💯 FREE Courses (100+ hours) - https://calcur.tech/free-courses 🏆 C++ Mastery Course - https://calcur.tech/cpp-mastery 🐍 Backend Python Course - https://calcur.tech/backend-python 🥇 Python Mastery Course - https://calcur.tech/python-mastery ~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~ ✉️ Newsletter - https://calcur.tech/newsletter 📸 Instagram - https://www.instagram.com/CalebCurry 🐦 Twitter - https://twitter.com/calebCurry 🔗 LinkedIn - https://www.linkedin.com/in/calebcurry ▶️ Subscribe - http://calcur.tech/subscribe 👨🏻‍🎓 Courses - https://www.codebreakthrough.com 🅿 Patreon - http://calcur.tech/patreon-calebcurry

💻 Source Code: https://cwa.run/nodebase 🎨 Free Assets: https://cwa.run/node-assets 🎥 Part 2: https://youtu.be/S-4DrLHtL1s?si=n4a7jM4FUWf9NN32 📚 Resources: Try Inngest: https://cwa.run/node-inngest Try Polar: https://cwa.run/node-polar Try Better Auth: https://cwa.run/node-auth Try Sentry: https://cwa.run/sentry Try CodeRabbit: https://cwa.run/node-rabbit Try Neon: https://cwa.run/node-neon In this tutorial, we're building Nodebase, a complete workflow automation platform from scratch. You'll learn how to create a visual drag-and-drop canvas for building workflows, integrate multiple triggers and AI providers, handle background job execution, and build a full SaaS business layer with authentication, subscriptions, and paywalls. We'll also cover error tracking with AI monitoring and a professional Git workflow with AI-powered code reviews. Key features: 🔄 Visual workflow builder 🎯 Trigger nodes (Webhook, Google Form, Stripe, Manual) 🤖 AI integrations (OpenAI, Claude, Gemini) 💬 Messaging nodes (Discord, Slack) 🌐 HTTP request node ⚡ Background job execution with Inngest 💳 Polar payments & subscriptions 🔐 Better Auth authentication 🎨 React Flow canvas 🗄️ Prisma ORM + Neon Postgres 🔒 Type safety with TypeScript + tRPC 🐛 Sentry error tracking + AI monitoring 🧑‍💻 CodeRabbit PR reviews 🌐 Next.js 15 App Router 📱 Production-ready SaaS Timestamps 00:00 Intro 06:05 01 Setup 29:33 02 Database 56:15 03 tRPC Setup 01:35:21 04 Authentication 02:37:24 05 Theme & Styling 02:55:05 06 Background Jobs 03:28:09 07 AI Providers 04:01:53 08 Error Tracking 04:27:54 09 Sidebar Layout 05:06:26 10 Payments Setup 05:44:04 11 Workflows Crud 06:45:20 12 Workflows Pagination 07:34:34 13 Workflows UI 08:23:40 14 Workflow Page 08:59:36 15 Editor Setup 09:50:42 16 Node Selector 10:40:32 17 Editor State 11:59:20 End of Part 1