RecipeGoogle Ads
Read the Google Ads change history properly
The change events log, filtered to the scope in question, attributed and dated.
IntentWho changed what, when, on what — the account's black box recorder.
- 2
- Steps
- 1
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- Before blaming performance on the market.
- After onboarding: what the previous team did on the way out.
Do not use it when
- Beyond 30 days back: Google keeps 30 days, absence of records is not calm.
What it needs first
Required
Preconditions
- The account is ticked in the dashboard, confirmed via list_accounts.
Inputs
window- Analysis window.Default: last 30 days.
Procedure
In order. Every tool named is one the gateway ships, and links to its reference.
Pull change events for the window and scope.
Group by actor and by resource, then align dates against performance moves.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
A change lands within 24-48h of a performance move on the same scope
Conclude
Primary suspect: name it, date it, check magnitude before closing.
Evidence every conclusion must carry
- Every figure carries its account, metric and window.
- Anything below a readable sample size is reported as unjudged, not as zero.
Where the agent stops
- The readout changes nothing. Any change it motivates goes through Safe Writes: preview, human confirmation, then apply.
How it goes wrong quietly
The cases where the analysis is wrong and still looks right. Read them before trusting a number.
- Automated rules and scripts appear as their owner's account: an 'actor' can be an automation.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.