
From Google Ad scripts to Kimi Code
How AI tools moved me from writing one-off Google Ads scripts to building repeatable AI performance marketing systems, and what I built around them to make the work reliable.
8 of 23 posts

How AI tools moved me from writing one-off Google Ads scripts to building repeatable AI performance marketing systems, and what I built around them to make the work reliable.

Set up Meta Conversions API (Facebook CAPI) for lead ads, instant forms, standard events, offline conversions and Event Match Quality — with or without a CRM.

I built a pipeline that lands Meta Lead Ads in a Google Sheet and sends WhatsApp alerts to the sales team within seconds. No CRM, no Zapier, no monthly middleware bill.

The Google Ads API path for first-party data upload is dead. Data Manager API is the replacement. Here is the grounded, practical stuff from a pipeline that is now running in production.

I moved campaign checks, reporting, conversion uploads and lead qualification into terminal commands. This is how I run Google, Meta and LinkedIn ads from the command line.

This is an update to the previous article and the more simpler tagmanager monitor I built, and with some additional learnings, I added more robustness to it Google Tag Manager usually breaks quietly.

A custom Zsh shortcut that opens the right folder, activates your environment, and starts JupyterLab. No more hunting for the latest script version.

Reporting is one of the most tedious parts of performance marketing. Here's a Google Ads script that pulls campaign metrics straight into a Sheet, a reasonable first script if you've never touched Ads Scripts before.