What are your experiences with the debugging hell loop when the ai agent gets lost?

How do you avoid that or get baxk on track?

Comments URL: https://news.ycombinator.com/item?id=45004300

Points: 4

# Comments: 1

Right now the most relevant mapping process I have to do is taking Amazon product data and transforming it to a Shopify upload csv.

The largest of these is around 20k rows, so nothing crazy.

There are apps that do this via APIs, but at a large enough scale, they are not reliable.

The process takes around 10 hours, with the help of a VA who does the lower level cleaning stuff.

I made a bare bones spreadsheet with under 10 columns, which makes it much easier to work with the data.

Once I'm satisfied, I run it through a python script, which turns it into a Shopify conforming csv.

Because of different needs of clients, I almost always have to modify the script, but less and less each time, and Cursor makes the edits pretty easy, as long as I review each proposed change and prevent it from getting the script.

Good thing about cursor is that it can run its own tests against the input csv in agent mode and debug autonomously.