LLM Application Development Experience Sharing Session

If you want to create your own AI service without coding, this course is the perfect solution. Using the Dify no-code platform, you can create high-quality AI apps with just your ideas. Instead of complex theory, it's structured around hands-on projects, allowing both AI beginners and working professionals to develop practical skills.

Latest version as of October 2026. This is a 299-lesson course created by YouTube’s “AI Adjunct Professor Lee Jong-beom” (54,000 subscribers). It guides you step by step, starting with how to open a browser tab and progressing to creating an AI employee team with Claude Code. It includes approximately 290 practice worksheets and 1,000 credits.

This is a practical course on building a RAG-based document search system using the OpenAI API and Spring AI in a Spring Boot environment. You will learn the entire process of developing an AI assistant step by step, from the concepts of Prompt Engineering, Vector Stores, and Embeddings to rapid prototyping with Dify, MCP tool integration, multimodality, and guardrails. You can learn practical application strategies by comparing direct implementation with the use of no-code tools. 🆕 [Update] Section 4 now includes a supplementary lecture (1 hour) on TypeSafe’s Jev decision-making model, covering how to design an agent’s decision-making logic in greater depth.

We are truly in an era where anyone can create their own service in just a single day. In the previous Vibe Coding workshop, the goal was to experience firsthand what Vibe Coding is all about, and for everyone to complete and deploy the frontend (the visible pages) of the service they wanted to build. This upcoming workshop goes beyond simply creating a service that looks good. It focuses on a development approach that emphasizes imagining specific actual users and asking, "Who will use this service, and why?" Through the workshop, participants will learn how to clearly define their target users and the problems they aim to solve while building their own services. It’s perfectly fine if you’re new to Vibe Coding! You don't need to know how to code or understand development. Experience more than just following along—come and create a truly functional service yourself at this workshop!

We invite you to the fascinating world of coding where you analyze and visualize financial statements using only prompts. Without a single line of code, you create and deploy a service in consultation with AI.

No development knowledge needed! Create your own automation system in just a few clicks.

Develop various features using Spring WebFlux. This course will teach you WebFlux's essential concepts and practical implementation.

During the Gold Rush, it was said that it was easier to become rich by selling gold mining tools than by mining gold yourself. How about selling programs in the ChatGPT Age of Exploration?

Which AI tool should I learn first? Stop worrying now! - Rated 4.8 by 80 students ⭐️⭐️⭐️⭐️⭐️ - ChatGPT, Claude, Gemini, Genspark, NotebookLM, Gamma, Skywork, Manus, Antigravity, Claude Code, MiriCanvas, Opal, CapCut, and more - Learn the core features of over 15 tools very easily over 20 days. - Through weekly assignments, we provide a course you can "internalize" rather than just "passively listen to." - All-in-one coverage: Prompt Engineering > Image Generation > PPT & Video Creation > Vibe Coding - 4 hours of lecture videos + weekly study materials + assignment certification system

To avoid making a definitive diagnosis based on a single response, compare the input conditions, repeated results, errors, and logs. Observe direct and indirect prompt injections and create one evidence-backed Mission 4 diagnostic record. The hands-on environment from Part 1 and the threat model document from Part 3 are required.

We examine AI security incidents and the role of red teams, then set up an LLM practice environment in our own AWS account. From capturing the initial response to checking usage and cleaning up resources, we record everything in the Mission 0 checklist. The prompt injection diagnosis exercise continues in Part 4.

This is the actual process of taking the HYBE–Min Hee-jin–NewJeans dispute, previously seen only in the news, assigning Claude to investigate it along four separate lines, and organizing “court rulings” and “claims” into a single table. When I encounter unfamiliar terms, I ask about them using the article’s exact wording and translate them into numbers; when articles report different judgment amounts, I check the case numbers and original texts. At the end, I compare seven contract-related lessons from the case against my own contract (as of October 23, 2026).

From AWS EC2 backend operations to automatic error fixing, we are revealing the entire development process of Sidabari (https://github.com/cx8537/sidabari), a Claude Code-based automation tool. In this course, we provide all the actual prompts and conversation history used as learning materials, allowing you to experience the entire prompt input process involved in its creation.

A practical UI design masterclass that helps you avoid violating Korean law or getting caught up in refund disputes after copying the signup forms, pre-tax pricing tables, and seven-click cancellation modals of famous overseas SaaS products. It compares the original texts of the amended Electronic Commerce Act (which took effect on February 14, 2025, and prohibits six types of online dark patterns), the Personal Information Protection Act, and the Act on Promotion of Information and Communications Network Utilization and Information Protection (KISA’s 7th edition of its guidelines) against 16 real-world screenshots from nine Korean and international services, one by one. It also provides five ready-to-copy Korean UI text templates, a 12-item pre-launch checklist, and three AI audit prompts.

Create a program using the GPT API, and even generate images and videos!

LLM: A pro quickly delivers core content, from essentials to practical tips!

Build a Saju (Four Pillars of Destiny) analysis AI agent that integrates Manseryeok, Astrology, Zi Wei Dou Shu, Onomancy (Name Study), and MBTI using n8n workflows and Python algorithms. We will complete a production-level service system from start to finish where 13 specialized agents collaborate to generate professional-grade Saju reports.

From tokens and context to RAG, agents, and guardrails, we examine how AI services work from a security perspective. We compare the concepts with the provided backend code and organize the areas to inspect across input, retrieval, and tool calls into a single attack-surface map.

When you try to bring together content scattered across your blog, Instagram, and Notion, why does asking AI to build a website without coding produce the same purple gradients, glass effects, and emoji overload (AI slop)? We’ll break it down and, using the code from the live static sites ainewground.com · gptssam.com, build a DESIGN_RULES.md design constitution, a single-JSON static build with a ✔/△ source-separation accordion, a GuideGate with instant, zero-second unlocking and email typo correction, a KakaoTalk 1200×630 preview card, and a three-step deployment check—in just 14 minutes.

Simple tutorials alone make it difficult to apply in practice. I will clearly pass on my professional know-how, covering complex state management and multi-agent design methods.