[Beginner’s Guide] Building an Investment Research Assistant for Fund Managers — A 24/7 Stock Bot Powered by AI, No Coding Required

There are so many stories saying, "Automation is just one click away." However, it's easy to give up when you actually try to apply it to your own work. We have captured the raw record of a team that spent six weeks narrowing the gap between "it works" and "I am using this for my work!"

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.

Bots are harder to keep running than to build. This covers how to operate bots you can trust for the long haul—from health-check bots and real-world outage cases to cost and security management, market-regime gauges, and backtesting.

Learn how to send bulk emails using Python and the Gmail API, and collect and automate data using bs4, requests, slack api, and Github Actions.

When AI says “implementation complete,” do you take it at face value? This Step 2 course has Claude Code and Codex handle everything from understanding the repository to implementation, testing, review, and PRs, while teaching you to evaluate results based not on completion descriptions, but on the scope of approval, execution evidence, and change risks.

I handed the labor-intensive parts over to AI and embedded affiliate links in the articles. I’ll show you everything about the blog automation system built by a non-developer.

If you follow OpenClaw Parts 1 and 2, you eventually end up making a single agent do everything. As you do this, there comes a moment when prompts get tangled, memory gets mixed up, folders get messy, and you feel stuck, not knowing how to organize things anymore. This lecture is the "Introduction to Multi-Agents (Part 2.5)," designed to help you move one step further from that point. While maintaining a single bot, we will separate roles into two agents—planner and editor—and connect each agent to different workspaces and Telegram forum topics. You will personally build a structure where "different agents respond depending on which room you speak in." By following the hands-on practice, you will have the following in your environment: - A configuration file defining two agents: `content_planner` and `content_editor`, - A content folder structure where planning and drafting are separated, - A Telegram group chat where different agents are attached to specific forum topics, - And one actual draft of an Inflearn course introduction created through the collaboration of the two agents. In short, this is a practical class that helps you design the first step of upgrading your Telegram bot from a "single AI assistant" into a "small AI team with divided roles."

Instead of writing longer prompts, I create rule files, logs, permissions, hooks, and validation routines one by one whenever something goes wrong in a real project. With a news alert bot that I actually built and deployed to a server in five days, 211 screenshots and 87 instructions exactly as originally written.

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.

Can you make a proposal look convincing with AI, but lack the confidence to bring it into the meeting room? A global content strategist with 17 years of experience—who built practical planning expertise at major advertising agencies and global e-commerce companies, and had that expertise validated on a global education platform—will teach you the principles of planning that work in practice and AI workflows, from defining the problem to completing the slides.

You may have heard that "AI is amazing," but you might not know what is actually happening or what you should be doing—this is a practical introduction for those people. Part 1 explains the cutting edge of AI, as well as Antigravity and Claude Code, where AI takes action directly on your own computer. Part 2 features a screen-recorded demonstration of the entire process of creating an AI slide presentation and narrated video from a single article.

Built with AI but worried about security? You’ve come to the right place. Drawing on the real-world expertise of a senior developer at a leading Korean tech company, we explain the security issues that can arise in AI-built services in an easy-to-understand way. We also provide prompt guides to help you review your project and strengthen its security right away.

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.

AI writes on Slack and Notion for me? Work smarter with MCP, which goes beyond the limits of existing AI!

This course teaches non-developers how to properly build, operate, and monetize a service using Claude Code. It provides template repositories and operational know-how so that non-developers and beginner developers alike can use Claude Code at the level of the top 1% of developers. This course will be especially helpful for those who want to build a service with Claude Code at a truly “professional developer” level; those who want to create a service capable of generating revenue through a one-person business or side project; those who have built something powered by an AI agent like Claude Code but are stuck because they lack the know-how to operate it properly; and those who feel overwhelmed as their solo project grows because bugs keep occurring and things become difficult to control whenever they add new features. The course also covers how to build a foundation for monetization and provides guidance on operating the service under the assumption that real customers will be using it. Once you have actual customers, processes such as monitoring errors occurring on the production server, server status, and logs are essential. However, there are surprisingly few places that teach these processes. In my course, along with this kind of detailed and professional operational know-how, I also explain how to enable AI to observe these monitoring metrics and data and take appropriate action.

[Final Goal] Build an operational agent that handles the full cycle: fault injection → alert → initial AI analysis → runbook and remediation plan → human-approved action → postmortem draft. Run the virtual commerce platform 'Loop Market' with Docker and practice using Prometheus, Grafana, Loki, and Claude.

Automate the entire short-form video production process with zero video-generation costs—no expensive AI tools required. We help you build an affordable automation system, even if creating and monetizing Shorts feels overwhelming.

This course covers implementing combat, UI, data, and server functionality for a Unity idle game using CLI- and MCP-based AI tools. You’ll learn the entire process of applying Firebase, ads, in-app purchases, and Addressables to launch a mobile game on Google Play.

This course is for solopreneurs and marketers who are exhausted from creating content every day. Send a single topic line to Telegram on your phone, and build a bot—without coding—that returns ten card-news slides, a caption, and a 40–50-second short. The instructor has transferred the design rules and review mechanisms from the bot they operate themselves, prompts and all, and verified that it works from scratch, starting with an empty folder and running all the way through to producing the final content.

Start by installing the Claude desktop app and getting familiar with its interface. Then learn what’s changed with the all-in-one Claude and understand the difference between an AI you ask questions and an AI that does the work. PART 1 In “Giving Clear Instructions,” learn how to delegate work to Claude through a single chat window—from writing work requests and assigning files and research to getting finished documents, slides, and spreadsheets. PART 2 In “Connecting Claude to Your Work,” use memory and projects to teach Claude your rules, and connect it to your real work environment—including data analysis, email, Drive, Calendar, folders on your computer, and web-based work. PART 3 In “Handing Off the Whole Task,” delegate major tasks all at once and use skills, scheduled tasks, and work dashboards to automate recurring work—creating a workflow where people only need to approve the results. Each session centers on the instructor using Claude to handle work they’re actively doing, and includes examples of applying the same methods in corporate and school settings.