Practical AI Agent Workflows Starting with OpenAI Codex

Rapid app development with SwiftUI!

With just a video clip, an Apple MacBook, and Final Cut Pro, you can create any video. Come and explore the world of Final Cut Pro! ✈️

The time when your imagination becomes reality—we invite you to the world of 'Vibe Coding.' We have prepared this lecture for those of you who "don't know coding, but know exactly what you want to create." With the emergence of AI like ChatGPT and Claude, people say anyone can develop. But what happens when you actually try? - "It writes simple code well, but as the number of files increases, the AI forgets the previous context." - "It looks plausible, but it throws errors when executed, and when I ask to fix it, it gives even weirder code." You’ve likely had this experience at least once. I also experienced the same frustration when I first collaborated with AI. AI was an excellent 'assistant,' but it had limitations in seeing the big picture. However, after discovering the OpenAI Codex CLI and mastering a new method called 'Vibe Coding,' my development process changed completely. This lecture will solve the problems you are facing and transform you from a coder into a director who commands AI agents. Equip yourself with the powerful tool called Codex CLI and join me on an exhilarating journey of Vibe Coding to turn your imagination into reality.

It's okay if you don't know a single line of code. We are now in the era of 'Vibe Coding,' where you develop by 'conversing' with AI.

Complete a company introduction landing page with hands-on vibe coding. Using Cursor AI + Next.js + TypeScript + TailwindCSS + shadcn/ui + MCP stack, proceed from design to deployment all at once. The key is "fast implementation + SEO foundation that performs well in search engines." 🏁 Course Objectives Landing creation → Performance optimization → SEO implementation → Deployment/Indexing Real-time coding (vibe coding) to immediately check completed sections Direct experience including search indexing 🛠️ Practice Stack Cursor AI, Next.js(App Router), TypeScript TailwindCSS, shadcn/ui, MCP workflow 🔍 SEO Practice Apply SEO optimization MD files provided by instructor Metadata, OG/Twitter cards, robots/sitemap, structured data (JSON-LD) Optional multilingual routing implementation 🎯 Final Product Responsive company introduction landing + contact form Target Lighthouse 95+ Vercel deployment followed by Search Console registration and indexing request 📚 What You'll Learn from This Course How to quickly compose hero/trust/features/FAQ sections Clean UI composition with shadcn/ui Form validation and basic conversion tracking point design Boosting SEO scores with structured data + multilingual routing Understanding the indexing process through Search Console after deployment 💡 Industry Insights (Course Bonus) Beyond just code implementation, we'll briefly cover marketing and exposure methods actually used in the real market. Realistic pricing ranges for advertising, blog posting, and comment work How outsourcing and contracting companies actually proceed with SEO and exposure work Cost/efficiency differences between direct developer participation and outsourcing Through this section, you can develop a sense of how technology is actually utilized in real industry work and what cost structures drive it, beyond just the technical aspects. One-Line Summary Following the flow of "implementation → optimization → deployment → indexing," learn the web creation process that connects to actual search exposure and real industry market structures.

I created 3 services in 3 months conversing with AI. Without needing developers or coding, build practical web services with AI.

Learn a practical web production workflow that can be applied immediately in the field—from homepages, landing pages, and interactive websites to AI Agent-based CMS—using AI image/video generation tools and Vibe Coding. This course is not just about creating a single screen with AI. It covers the process of generating images and videos using the latest AI tools such as OpenAI Images 2.0, Kling, and Higgsfield, and utilizing them as hero images, background videos, transition videos, and interaction assets for actual websites. Based on Next.js, you will step-by-step implement cinematic landing pages, game-like interactive homepages, inquiry pages, and blog content pages, mastering structures and workflows that professionals can refer to immediately when creating homepages or landing pages. In particular, this course does not stick solely to traditional admin-page-style CMS. You will implement an AI Agent-based CMS structure where AI Agents like Codex and Claude Code organize content and image assets based on predefined skills and upload rules, then upload them to Neon DB and Vercel Blob Store. In other words, instead of an administrator manually entering data into forms one by one, you will experience an operational method where you provide blog topics, reference materials, and image assets, and the AI Agent organizes the content structure and uploads it in a consistent format. Later, this structure can be further enhanced into traditional admin pages, approval workflows, or automation pipelines as needed. Furthermore, it doesn't end with production; we will prepare elements necessary for actual operation, including Vercel deployment, GoDaddy domain connection, SEO meta tags, favicons, OG images, sitemaps, and robots.txt settings. The course also covers the process of registering sites and verifying ownership on Google Search Console, Bing Webmaster Tools, and Naver Search Advisor, as well as setting up Google Analytics and Google Tag Manager to track visitor data. By the end of the course, you will be able to independently reproduce a professional web production workflow that spans AI-driven planning, image/video asset creation, Next.js implementation, SEO optimization, deployment, search engine registration, analytics tool setup, and AI Agent-based content operation.

This course is for those who don't know much about development but want to start "vibe coding," and for those who want to personally create a landing page to promote their own business (restaurant, cafe, etc.) or service (lawyer, accountant, hospital, etc.). I will help you establish the perfect starting point for vibe coding.

This course is not about non-developer office workers learning coding itself, but rather an education focused on developing the ability to solve business problems directly using AI agents. Previously, one had to rely on IT departments or outsourced development when problems arose, but we are now in an era where you can design alongside AI and create immediate prototypes to implement task automation. The core competencies required for this are problem definition, establishing solution strategies through AI collaboration, and the ability to build the necessary tools yourself. In particular, by utilizing Codex CLI, existing ChatGPT users can practice agentic coding immediately without additional costs, allowing non-developers to quickly gain practical experience. The curriculum is structured step-by-step, covering everything from understanding changes in the AI agent era to development basics, terminal usage, Codex CLI-based agentic coding, problem structuring, Django web app development, and the creation of actual task automation apps. Learners can secure task automation capabilities by directly building applications applicable to real-world work, such as To-Do lists, checklists, schedule management, meeting minutes, and summarization tools. The entire course is designed as a modular micro-learning system composed of short units, allowing for rapid learning of necessary content and immediate reuse during work.

"Data analysis—don't stay trapped in complex Python syntax and Excel functions anymore." This course is a practical masterclass that automates the entire process of data processing, from Excel and Google Sheets to Python-linked analysis, by hiring the latest AI agents as your own dedicated data analysts. Instead of difficult coding knowledge, we introduce the latest 'Vibe Coding' method—commanding as if having a conversation in natural language—allowing even non-majors to enter the world of data analysis without any barriers. Through comprehensive hands-on practice using actual business data—covering everything from data preprocessing and visualization to report writing—experience a powerful AI workflow that you can apply to your work starting tomorrow. A lecture utilizing AI agents, Excel data analysis, chatGPT, Gemini, (Python), Genspark, Google Colab, chatbots, Google Antigravity, and notebookLM.

Non-Majors Welcome: Real-World Vibe Coding Projects Created Through Conversations with AI

"Why did the AI write this code?" or "Why can't it remember what I just said?" The frustration you encounter when using AI tools like Claude Code stems from not knowing how the tool actually works. This course flings open that black box. Over 25 lessons, we will build our own Coding Agent from scratch that functions exactly like real-world professional tools—giving the LLM 'eyes' to see files (Read), 'hands' to fix code (Edit), and 'feet' to execute commands (Bash). This isn't just about learning how to use a library. You will gain hands-on experience by implementing code to understand how AI perceives project structures, why it loses its memory during long conversations, and how to solve those issues technically (Sliding Window, Summary). Through this process, you will evolve from being a mere 'user' of AI tools to an 'AI provider' who understands the underlying principles and can customize and evaluate tools to fit your specific needs.

No coding knowledge needed! This lecture shows how anyone can easily create a website using AI tools 'Cursor' and 'Vibecoding'. Follow 2 practical examples to build a real-world website with just clicks, and even learn to deploy it.

With v0, cursor AI, and various LLMs, from PRD to AI product recommendations! Complete your Next.js shopping mall through a practical project.