Run the daily morning check across accounts
The daily sweep: delivery, spend pace, rejects, anomalies overnight, in minutes.
IntentOvernight surprises caught before the client sees them.
- 2
- Steps
- 4
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- Every working morning on managed accounts.
Do not use it when
- Deep analysis: the morning check finds, day work explains.
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.
Check delivery status and overnight spend everywhere.
Flag anything outside normal bands to a human, with links.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
Overnight spend deviates hard from the daily norm
Conclude
Flag first, investigate second: the morning check's job is speed, campaign-anomaly-investigation does depth.
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.
- Overnight windows under-report conversions everywhere: pace on spend, never on CPA, before noon.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.