RecipeMeta Ads
Read Meta ad-level performance with creative names
Ad performance with the creative behind each ad, the table creative discussions should start from.
IntentAd-level results joined to their creatives, so findings name assets.
- 2
- Steps
- 3
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- Creative reviews.
- Before pausing 'the bad ads'.
Do not use it when
- Below ~1,000 impressions per ad: rank, do not judge.
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 ads with their creative links.
Join creatives and performance.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
The same creative runs in several ads
Conclude
Aggregate by creative before ranking: the asset is the unit, not the ad ID.
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.
- Dynamic and Advantage+ formats assemble variants: the 'creative' is a recipe, and variant-level truth is partial.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.