⚠️ This column is a sharing of the prompt creation process for free educational purposes, and is not any investment, legal, or financial advice. AI execution results may contain errors and independent verification is essential, and all responsibility for use is entirely attributed to the user. It cannot be used directly for business decision-making. [View all mandatory confirmation items below the 30-week timeline before use[]](https://www.notion.so/30-29f84ddcec3c80a1a87eda9883d81453?pvs=21)
To create a new checklist by referring to Economic_Checklist.md, I requested structure identification with Sequential Thinking.
Economic_Checklist.md had a clear structure. It was divided into PART A and B, and each STEP was arranged sequentially. I thought I could apply this structure to HTS_Checklist.md as well.
STEP 1 is searching policy documents. It searches for classification codes and retrieves related documents, but when I actually tried to think of search keywords, there was a problem.
Should I search for specific codes? It seemed too broad. Should I search for product fields and codes together? This is also too wide. I don't know specifically which product's classification code I need to find.
I requested Sequential Thinking. 'What do I need to do first to search for HTS classification codes?’
Claude started thinking. "1st thought: To search for classification codes, I need to know what Product is first.", "2nd thought: Product_Article.md has a product list.", "3rd thought: Economic also read Product first, read Product_Article.md and searched for economic data for each product."
"7th thought: Classification codes also need the same approach. Product must be read first.", "10th thought: I will define this as STEP 0.”