Urgent.News

What's breaking now, across thousands of outlets.

Editions

AI

I built an AI Shopify audit tool, then decided to take it back into my own hands

Most Shopify audit tools give you a polite report. Vetta roasts your store instead and tells you exactly how to fix what's broken. A few weeks ago, I built Vetta an AI-powered tool that audits Shopify stores for conversion issues. Instead of a standard “here are some insights” report, it bluntly calls out where your store is bleeding money, then gives you actual solutions to fix it. I built the…

Most Shopify audit tools provide a polite report. Vetta, on the other hand, takes a different approach by harshly critiquing your store and explicitly outlining the steps necessary to rectify any issues. A few weeks ago, I developed Vetta, an AI-driven application designed to scrutinize Shopify stores for potential conversion problems.

Unlike conventional tools that merely present insights, Vetta boldly highlights where your store is losing money, subsequently offering actionable solutions to address these issues. I constructed the initial version within a single session utilizing Emergent.sh. The fundamental functionality was accomplished, the application was operational, and I could achieve a considerable amount without constructing everything from the ground up.

However, a challenge emerged: while the interface functioned adequately, I was unsatisfied with its design and the prospect of making continuous alterations that would consume tokens. Consequently, instead of persisting in spending tokens on modifications I eventually intended to manage independently, I opted for an alternative course of action.

I transferred the code to Git and commenced working on it directly. This transition proved to be intriguing. Emergent facilitated the swift progression from conception to a functional product. Git and my own development process provide me with greater control over the subsequent developments, which proves to be crucial for a project where both the tone and design hold as much significance as the underlying logic.

Although I continue to learn the codebase and navigate through the process, this phase aligns with the project's overall objective. My intention isn't to construct the ideal app in one go; rather, I aim to grasp the extent of what can be accomplished, identify where AI can expedite the procedure, and acknowledge the areas where I must still delve deeper into the technical aspects.

Vetta commenced as an AI-generated endeavor. Currently, I am transforming it into a project I truly comprehend.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

More from Thursday 20 August →