RecipeMeta Ads
Review Meta brand safety controls
Brand safety controls read against the brand's written rules: blocklists, inventory filters, exclusions.
IntentWhat the account excludes and allows, against brand policy.
- 2
- Steps
- 1
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- Quarterly.
- After brand-safety incidents anywhere in the industry make clients call.
Do not use it when
- No specific contraindication beyond the preconditions below.
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 the account's brand safety controls.
Compare against the brand's stated policy and note gaps.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
Inventory filter sits at the loosest setting with no documented decision
Conclude
Flag as an undecided default, not a choice: someone should own it explicitly.
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.
- Controls differ per placement: a check at account level can miss placement-level gaps.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.