Recipe
Sweep creative performance across every platform
Creative results joined across platforms: what wins where, which winners never travelled.
IntentThe best and worst performing creative everywhere, one ranked view.
- 2
- Steps
- 5
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- Monthly creative councils.
- Before production briefs.
Do not use it when
- No specific contraindication beyond the preconditions below.
What it needs first
No single source is required: this one reads across whatever you have connected.
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 creative-level results per platform.
Rank winners per platform and list the untravelled ones.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
A winner on one platform has no equivalent elsewhere
Conclude
The cheapest test in the account: adapt and ship it there, sized as a proposal.
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.
- Formats do not translate literally: a 9:16 TikTok winner is a hypothesis on Pinterest, not a certainty.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.