Learn the entire process of building AI-callable business tools, from the concept of MCP (Model Context Protocol) to implementing a TypeScript-based custom server using Antigravity. Through a brand copy review example, you’ll develop practical MCP skills that can be applied immediately to automating repetitive tasks, integrating internal company data, and connecting APIs.

This covers how to use ChatGPT not merely as a question-and-answer tool, but as a thinking tool for structuring problems and comparing and validating multiple possibilities. Instead of memorizing prompt formulas, you will learn the workflow of collaborating with AI through actual conversations and practice the entire process—from defining the problem and separating roles to comparison and validation—in 30 minutes.

You don't have to say "summarize this" every time. In this lecture, you will learn how to create your own AI agent in Antigravity and use it immediately without repetitive explanations. The course is practice-oriented so that even beginners can follow along. https://antigravity.google/download (You can download the Antigravity Editor here :))

In this lecture, you’ll see in practice how AI agents can use the Browser MCP built into Antigravity to open a real browser and research and make judgments on the web. Rather than merely covering how to use it, the focus is on understanding the execution flow from Agent → Tool → Browser and the MCP-based extensibility structure. In 30 minutes, you’ll go beyond the concept of browser automation and structurally organize “how AI uses the web as a tool.” https://antigravity.google/download

A 30-minute free introductory course that starts with just the OpenAI API. Quickly learn the essentials—from the Responses API and JSON response handling to validation, idempotency, and logs—and learn a practical backend workflow that you can test right away without external service keys.

Full-stack course from Figma design to AI-powered coding and deployment!! [Figma + Vibe Coding (HTML/CSS/Tailwind/React) + Git + Vercel Deployment] Your design exactly as it is!! Complete it with Vibe Coding without a single pixel of error! A full-stack guide to increasing practical productivity by 5x using AI! You too can become a full-stack designer capable of both design and coding. ✅ Implement your design intent without a single pixel of error ✅ Design architecture that AI understands ✅ Prompt engineering skills to precisely control AI ✅ Ability to skillfully fix code generated by AI Experience the amazing reduction of time from design to coding and deployment by 1/5.

Do the results of vibe coding keep turning out differently from what you intended? Learn a workflow that uses specification-driven development (SDD) and Spec Kit to define goals, scope, business rules, and completion criteria, then shares the same specifications with Claude Code and Codex to reduce repetitive revisions.

Are you feeling stuck trying to implement an agent that goes beyond a simple chatbot? Based on my own trial and error and know-how from official documentation, I will show you how to build intermediate-level agents that can be immediately applied to real-world tasks.

Using ChatGPT is completely different from developing an actual generative AI service. This is because you must master everything from API calls to conversation state management, structured outputs, function calling, document-based RAG, MCP integration, and AI agent implementation. Based on extensive experience in data analysis and AI instruction, this course explains complex concepts through Python-centered practice. You will learn step-by-step—from the principles of generative AI to the OpenAI Responses API, multimodal features, File Search-based RAG, external tool integration, and the Agents SDK—to complete a fully functional AI application.

This course is a practice-oriented lecture that goes beyond 👉 just explaining the concepts of RAG (Retrieval-Augmented Generation), 👉 to building the actual working architecture yourself, 👉 and experiencing expansion and optimization. Starting from simple RAG examples, you will learn step-by-step—from Advanced RAG to Modular RAG and Agent-based RAG—at a level that can be immediately applied in the field.

Let's create a service that improves itself even while you sleep! Learn step-by-step how to build a 24-hour vibe coding system using loop engineering with Codex.

Innovation in Work Efficiency and Creativity – Agentic AI AI is now evolving beyond simple automation into a new stage where it can judge and execute on its own. Agentic AI is at the center of this change, serving as a core technology that helps businesses and organizations operate smarter. In this course, we have organized the content clearly and simply so you can understand how Agentic AI connects decision-making with execution and how it can be applied to practical work. Discover the essential knowledge for every professional preparing for the future right now.

We will summarize the theoretical concepts of MNIST, the most fundamental dataset in computer vision, and learn how to implement it using Torchvision's API as well as how to implement a custom dataset class directly.

Build your own Copilot Agent to automate the repetitive reading, organizing, summarizing, and drafting tasks that occur every day in a Microsoft 365 work environment. Learn how to create a practical work automation agent that delivers immediate ROI—not an ambitious AI project—and use it as your digital work partner.

Beyond a chatbot that simply generates answers, you will directly implement an autonomous AI Agent that makes its own judgments, calls tools, and performs multi-step tasks. You will learn through step-by-step practice, covering everything from OpenAI Agents SDK's Tool Calling, Handoff, Guardrail, Session, and Tracing to connecting external tools and databases using MCP, as well as LangChain and Deep Agents' Planning, Subagents, Filesystem, and Memory. The ultimate goal is to equip you with the ability to design and implement tool-integrated AI Agents that can be applied to real-world tasks.

Solve the point where 80% get stuck at makeathons. Complete Raspberry Pi · Computer Vision · LLM · 3D Design in 4 weeks! Achieve top rankings at makeathons with a demonstrable smart mirror PoC!

While LLMs are currently transforming the development environment, what truly matters is not just "writing code on your behalf" but integrating them as features into a service. This course provides a step-by-step guide to implementing a lightweight yet polished Tarot reading service using Next.js and the OpenAI API. In the first stage, we will build an MVP that works without a backend, connecting the user input flow (questions/threads/card selection) to result generation. In subsequent stages, we will expand the functionality by building a backend, implementing general login and OAuth, adding community features, and creating a reading dashboard. Finally, we will conclude by deploying to AWS and integrating Google AdSense to complete a service ready for actual operation. Additionally, we will cover understanding pricing structures and cost optimization strategies to ensure that LLM API usage costs do not become a burden.

Messy code, a flood of requirements... If you're looking for a breakthrough with AI, Learn how to become a "high-performing developer" by leveraging AI in legacy environments, taught by the former VP of Engineering at Toss Payments. Legacy code isn't going anywhere, even in the age of AI. It’s no exaggeration to say that every company has legacy code, unless they were founded today. So, how should we utilize AI in this reality? In this course, the former VP of Engineering at Toss Payments, who led a large-scale payment service organization, demonstrates firsthand how to work effectively using AI in legacy environments. This isn't just a course about how to use AI or basic coding skills. The goal is to help you develop your "critical thinking" as a developer and truly understand what it means to work effectively.

We explore how to create an AI judge by combining knowledge graphs, reasoning systems, and various agent frameworks such as CrewAI, LangChain, and AutoGen, which enable the implementation of LLM-based multi-agent technology.

"Beyond Data Analysis: From Predictive Model Design to Optimization (29 Lectures in Total)" Have you finished your data analysis but feel stuck when it actually comes to building a model? We help you fully master not just how to call libraries, but the working principles of each algorithm and optimal model validation strategies.

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

Learn the entire process of running the latest Gemma 4 model directly on your MacBook without the burden of paid API costs. You will master performance maximization techniques using Apple Silicon's Metal API and optimal parameter settings for different VRAM capacities, while gaining the ability to build production-level local AI infrastructure based on FastAPI.

This is a Silicon Valley internship and 30 Big Tech system design & open-source contribution mastery course that ensures job security even in the AI era. In this course, you will design and scale 30 real-world system designs using cases from Big Tech companies such as Netflix, Tesla, Meta, and Tinder. Finally, you will design your own service from architecture to DB and scaling.

This course covers implementing combat, UI, data, and server functions for a Unity idle game using CLI and MCP-based AI tools. You will learn the entire process of releasing a mobile game to Google Play, including the application of Firebase, advertisements, in-app purchases, and Addressables.

"How is a 1-trillion parameter model trained?" Discover the scaling strategy of Kimi K2.5, revealed directly on stage by Moonshot AI at GTC 2026, in Korean on Inflearn. 2x token efficiency · 1 million token context · 1,000 agent swarm The next step for open-source LLMs is here. * This lecture is released for free through an official collaboration between Moonshot AI, the creator of Kimi, and Inflearn.