Google Ads dip investigator
Give it your results and recent changes. Get the likely cause and a fix-or-wait call.
Google Ads dip investigator is a free AI skill for the job "Run Google Ads". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · Made by AI Blocks · Level: advanced · Thinking: high
What it does
When Google results drop, most people change many things at once. They look at yesterday, blame the budget, or rebuild the account. A rebuild resets learning and often makes things worse. This skill investigates in a fixed order. It reads the change history first, uses long time windows, and uses conversions by conversion time, because Google credits a sale to the day of the click, so the last 3 to 4 days always look poor. It then splits revenue into sessions, conversion rate and order value, finds which moved, and checks other channels and your site before Google. In Google, it looks at the top five campaigns by cost, finds the date things changed, and drills into the metric behind the drop. It ends with one sentence naming the cause, or it tells you to wait.
You give it
- The change history for the last 30 days
- Store revenue, orders, sessions, AOV and conversion rate over time
- Spend by channel, such as Meta, Google and others
- Google campaign data by week for 90 to 180 days, with conversions by conversion time
- Meeting notes (optional)
You get
- Findings in order, from the business level down to the root cause
- A fix, wait or ignore decision
- One sentence stating the root cause
Use it when
- Revenue or ROAS from Google fell and you do not know why.
- You changed several things and cannot tell which one hurt.
- You are about to rebuild an account and want to be sure that is needed.
How to use it
- Start a chat with the skill. Open it if you added it to your AI, or copy it and paste it in.
- Export the Google change history for the last 30 days and paste or attach it.
- Attach weekly Google campaign data for 90 to 180 days, with the conversions by conversion time columns.
- Add your store numbers and spend by channel for the same weeks.
- Change one thing at a time, using the fix it gives, and check again after the learning period.