AI Product Builder transformation records and AX execution insights
You don't need deep coding knowledge to build an MVP with AI. This guide covers planning documents, role separation, and validation criteria using ChatGPT, Claude Code, and Codex.
Read More →Lessons from building the Shorts / Reels Generator local MVP with Claude Code. Covers why operators must own purpose, validation, and completion criteria rather than focusing on the code itself.
Read More →The partial take-profit bug wasn't found by a code expert. It was found by an operator who noticed something wrong in the live logs — and then narrowed it down working with an AI. In auto-trading, AI collaboration isn't about delegation. It's about building a verification loop the operator can actually judge.
Read More →Partial take-profit logic was implemented and the config was enabled. It never ran because the intraday sell loop wasn't passing the actual position size or partial_sold state. In automated trading, 'the logic exists' and 'the logic actually runs' are two completely different things.
Read More →An insight on separating the main brand from anonymous experiment channels by using consistent operational names.
Read More →As AI tools multiply, role separation comes first. A new GPT window works as an external thinking space for divergence without inherited context, while Meta Chulbuji absorbs the results into existing projects as the operating HQ. The key was not blocking divergence, but building a structure that recovers it as an asset.
Read More →A strong-looking backtest is not enough reason to change an auto-trading strategy. The first question is not whether the number is attractive, but whether the number was produced under assumptions that match live trading.
Read More →Running Codex vibe coding practice revealed that AI coding agents move autonomously through the entire task when given a broad goal. The real capability in AI development is not prompt writing — it is designing the sequence of work, the permissions granted, and the stop conditions.
Read More →Before building Commit Hero, I designed the judgment structure first. Running Deep Interviews to set direction, then defining scope through Plan, Design, and AGENTS.md before implementation — the experience confirmed that the human role in vibe coding is harness design, not coding.
Read More →I suspected the KOSPI200 ETF benchmark was distorting the RS filter due to mega-cap skew. Switching to a universe-weighted benchmark made things worse — the market-cap weighted universe RS came out even higher than the ETF. The problem isn't which benchmark you use; it's that all common benchmarks carry the same skew.
Read More →Running the first AI shorts production experiment with NotebookLM and Google Vids/Veo revealed that the core of shorts production is not video generation itself — it is building a repeatable routine that connects script, source, video, subtitles, upload, and review.
Read More →An analysis of how a fixed MA20 deviation filter structurally blocks leading stocks during KOSPI surges, and why regime detection must come before stock screening.
Read More →The core insight from the first refinement of the stock auto-trading strategy engine: before chasing more buy signals, the system must explain why it did not buy.
Read More →An insight from the initial chulbuji.com Notebook setup: how to manage sources, where public URLs are limited, and how Notebook fits into the AI role assignment structure.
Read More →In AI collaboration, the point is not to use one tool less. It is to place each AI where it creates the most operational value.
Read More →An operating insight from improving the auto-trading program from a ₩5M seed structure to a ₩10M expandable structure.
Read More →The chulbuji.com logo experiment confirmed that the main logo and favicon should not be the same image — they are two elements of a brand system, each with a distinct role.
Read More →Draft with GPT and Gemini first, reserve Claude for advanced review and precise execution. A practical SOP for reducing Claude usage through role-based AI allocation.
Read More →Three months into AI collaboration — taking stock of what's working, what still needs building, and the shift from learning AI to operating with it.
Read More →One thing that's become clear from building and running an auto-trading system: my job isn't writing code — it's asking the right questions, evaluating expert AI analysis as operational direction, and issuing execution instructions to Claude Code. In vibe coding, the human's role is to set the judgment criteria and keep the AIs on course.
Read More →A trailing stop sell → cash recovery → RS-qualified buy rotation structure appeared in live trading for the first time. Three consecutive trailing wins, zero stop-losses. The next challenges: high-priced stock handling, holiday detection, and fixing the export bug.
Read More →The trailing stop sold at +0.84%. For a moment, it felt like a waste. But that reaction is the problem — if emotional regret can override evidence that a system worked as designed, the reason for building the system in the first place disappears.
Read More →A fixed take-profit rule and a trailing stop work against each other — one should be removed. This is an operational review of the structural conflict found during live account operation and the three-tier zone redesign that replaced it.
Read More →MAX_HOLD=5 was a ceiling, not a target. When a system runs to fill a number, it picks available stocks, not strong ones. Four positions down on the day KOSPI hit an all-time high proved it.
Read More →What I built: Regime scoring system (5 conditions) + cash ratio logic tied to total assets. What broke: Wrong balance field caused all orders to fail; duplicate sell orders stacked 18 times. What I learned: The filter that blocks overbought stocks also blocks large-caps in recovery.
Read More →One Claude Design Handoff feature closed the design-to-development gap. The result: an 8-screen app live in production in one day, without writing code.
Read More →You don't need to read code to find bugs. Today I fixed three auto-trading bugs in one day — by reading logs, describing what was off, and letting AI trace the cause.
Read More →Whether the system worked correctly became a more important measure than whether I made money. Live day 3 — what -₩61,800 confirmed.
Read More →Writing an idea into a spec kept growing the feature list. Moving it to a screen changed the question entirely — from 'what features does it have?' to 'will users know what to do here?'
Read More →On day one, the system did nothing. That wasn't a bug — it was the right answer. What one week of automated trading taught me wasn't how to buy. It was how not to.
Read More →April 15, 2:51 PM. Samsung Electronics was sold automatically. I didn't tell it to. The trailing stop fired in live trading for the first time. I'm verifying whether the strategy is moving as designed.
Read More →The real result today wasn't the one stock I bought — it was the three that got blocked. The MA20 deviation filter stopped SK Hynix at 16.9%, LG Chem at 7.2%, Samsung SDI at 9.4%. A day the system quietly prevented the wrong buys.
Read More →I shifted from chasing bugs one by one to a structure that separates judgment from implementation. My coding ability didn't change. What changed was where I focus.
Read More →Editing the code and having those edits actually take effect are two different things. What I learned from running an automated trading system wasn't strategy — it was operations discipline.
Read More →I didn't write a single line of code. But the skill I used most today wasn't coding. It was the ability to precisely instruct 'what to build.'
Read More →Consistency isn't a willpower problem — it's a structure problem. I realized that only after counting twelve unfinished things.
Read More →What making the ChulbujiRunning music video taught me again. The more I tried to pack into a single scene, the more it fell apart. AI collaboration isn't about finding the right sentence — it's about breaking scenes down, adjusting the flow, and pushing through to the end.
Read More →Cadence hit 3,648 spm. Pace swung between 3 and 14 min/km. The app ran — but the numbers couldn't be trusted. A day of fixing 5 bugs by directing multiple AIs, one step at a time.
Read More →I don't know how to code. I've never written a single line myself. But today, the app I built spoke to me. A field test record of Chulbuji RunBuddy.
Read More →4 hours. Questions only. A first-year AI builder's first deployed game — bugs included, fixed in 10 minutes.
Read More →The reason AI tools hit a wall wasn't the tools — the roles were blurred. A record of the day I designed a production pipeline where three emotional keywords are all it takes to get content flowing.
Read More →A lunch-break retrospective from someone who built a game without writing a single line of code. From 1-file magic to Z Fold finger feel.
Read More →A 5-week record of a human transforming into an AI Product Builder in the age of AI civilization
Read More →