Learn how to create presentation materials with AI using numerical rules and rule files instead of vague adjectives like “polished.” Use ChatGPT Work and Codex to build dynamic, interactive HTML presentations from start to finish, then export them as links, PDFs, and PowerPoint files.

Meeting minutes, emails, and quotes accumulate into a work wiki with sources?! Write your rules in an Obsidian vault and hand things off to Claude Code: each new piece of material updates the related notes, and the weekly report comes out in a single line.

This is not a course about adding one more AI, but about running models from three companies as one team. Hermes breaks down goals, gives instructions, and gathers results as the command center; GPT handles judgment and planning; Claude Code takes care of development and file processing; and Antigravity (Gemini) manages research and production pipelines. After installing Hermes, you’ll connect the three companies’ models and define their permissions and security boundaries, then assign them tasks in sequence—finding business partners, organizing emails and files, delegating development, and creating product detail pages and images—while establishing review criteria. In the final lesson, you’ll cover parallel delegation, troubleshooting, and real-world marketing cases from midsize companies, shifting from an executor who merely transfers results to an orchestrator who decides who does what and how the work should be reviewed.

I don’t do everything alone. I hire four AI employees suited to my work as Claude Code subagents and divide the tasks among them: research, writing, review, and organization. I don’t write a single line of code. First, I establish company work rules that all the AI employees must follow and create four employees with different roles. Then I have the employees hand off their work to one another through files, connecting the workflow so that the previous person’s output becomes the next person’s input, and I define review standards to build an asset that eliminates the need to re-explain recurring tasks every time. Finally, I run all four at once to complete a real-world project. Across seven episodes, including the orientation, I create results that remain as files—not merely answers in a chat window.

ChatGPT, which used to only answer questions, now works directly on my computer. I give it instructions in Korean without typing a single line of code and receive the results as files. This six-part series, including the orientation, explains Codex’s workflow of context, planning, execution, and deliverables, then covers everything from safely defining a working folder to organizing files, creating tables with sources, and setting up scheduled executions that run automatically at a specified time.

Even when using AI, the reason you’re still busy lies not in the tools, but in how the work is arranged. By asking four questions—roles, flow, handoffs, and exceptions—you can turn your work into a single blueprint, separate what can be handled by rules from what requires judgment, and reduce how often you need to call on AI in the first place. Use an Excel file containing 1,000 transactions to lock the standards into the tool and generate reports, break tasks down with sub-agents, and hand off what can’t be done to another AI, receiving only the results and carrying on. Finally, connect a messenger as the entry point and add four safety measures, completing the conductor’s role of calling on AI only where needed rather than handing everything over across eight installments, including the OT.

Claude Code handles judgment and execution, while n8n takes care of triggers, connections, and scheduling. By following the sequence of Concept → Connection → Practice, repetitive tasks are designed into a flow of Input → Judgment → Execution → Verification → Delivery. With error handling, retries, and human approval included, the system operates unmanned through scheduled execution. Even non-developers can build their own automation systems without having to learn coding from scratch.

Done in a single line of command. Hermes, the AI agent that remembers, automates, and grows on its own. Even if you are not a developer, you can become someone who 'delegates' work to AI starting today. SMARTFORK will be with you from installation to practical application.

Have you ever felt that while AI gives perfect answers, the copying, organizing, and reviewing are always left to you? Claude Co-work goes beyond the chat window to directly read, edit, and create files in your computer's folders. Even without coding knowledge, simply provide a goal and learn how to complete "tangible results"—from reports and Excel sheets to presentations—in just 8 sessions, covering everything from agent principles (planning, tools, verification) to practical application. Move beyond the habit of just receiving answers and gain the power to make AI work for you.

Everyone says agents are the trend, but why does your work stay the same? Have you been blocked by the "alien language" of APIs, stuck at tool installation, or found that what you learned doesn't translate to actual work? This integrated course connects the entire process into "one single path"—from the principles of API and communication structures to creating your own agent through Vibe Coding, and automating practical tasks like reports, Excel, and content with Claude Code. Whether you start from the basics or aim for professional application, you will complete the journey without interruption. (Windows recommended)

Have you always given up on household accounting after just three days, found Excel tedious, and felt that investment strategies were just too difficult? This is a practical course designed to help you manage your income, expenses, and assets as data with AI—even without extensive financial knowledge. AI will analyze and interpret your data, ultimately helping you create 'your own AI financial advisor' to make your own money management decisions.

Stop making mass-produced shorts that just repeat gacha-style content with a single click! This is an integrated introductory and practical course where you will understand the principles of how AI creates videos even if you don't know filming or editing. You will complete one YouTube video using Veo, Runway, Kling, HeyGen, and CapCut, and even create 'surviving AI shorts' that viewers watch until the end through LLM planning.