This is a mid-course review after completing up to Part 3. I learned about this course through an acquaintance who practices trend-following trading. Looking at the collection of prompts, it seems the instructor uses a similar trading style, which made me realize why my acquaintance recommended this specific course. I immediately felt that it is great to be able to start with a complete framework for an analysis system. However, the course I was expecting was one where I could learn how to build a customized system through "Vibe Coding." In contrast, I felt that this course focuses more on following a pre-determined system (methods/parameters) exactly as they are. In fact, while listening to the lectures, I found myself busy just copying and pasting the provided prompts into Antigravity. While the instructor explains the structure and why such a system was created, I find myself asking: "Am I actually understanding the parts needed for personalization later on through these lectures?" From that perspective, I think it would have been better if the course provided the coding programs to build the system identically first, but then focused on how to expand or modify each step for personalization. As it stands, I don't know which parts of the various .py files—which I assume(?) are working organically—are essential areas that shouldn't be touched, or which specific parts can be modified. This makes me wonder how I can go about changing this system. (On the other hand, I also wonder if Vibe Coding would just handle everything if I simply requested it...) It might be because I haven't finished the entire course yet. I hope to leave a more helpful follow-up review after completing all the lectures. *Below are the parts I wanted to build that seem to align with this course: 1) Stock Filtering: Accumulating stocks retrieved from a brokerage API's conditional search or personally picked stocks (manual picks registered via Telegram integration). 2) Chart Patterns: Updating methods to digitize various setups through conversation with a separate LLM to determine if they match daily chart patterns. 3) Telegram notifications when a specific price point is reached after a matching pattern occurs. -Additional Content- I see the following in the course description. Since I built it using Gemini in Antigravity instead of the Claude CLI, there might have been more things I had to check manually in between... For now, I should continue with the lectures. In Lectures 1–3, you will experience creating a stock program exactly as it is using the prompts in the files I provide. From Lecture 4, you will begin to learn how to use prompts and the "Why" behind writing them this way. ✅ Real Data Handling: Building a pipeline to collect and process real-time price data for all 2,500 stocks. ✅ Advanced Logic: Implementing a scoring engine that crawls news data, performs AI sentiment analysis (positive/negative), and quantifies your own investment strategy. ✅ Full Automation: From building an API server to web dashboard visualization and automated Telegram reports delivered every morning.