Prepare accounts for a seasonal peak in one pass
The pre-season sweep: where budgets cap, what is still learning, what the feeds reject, weeks ahead.
IntentBudget headroom, learning stability and feed health before the season, not during.
- 3
- Steps
- 6
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- 4-6 weeks before the account's known peaks.
Do not use it when
- Mid-peak: the time to change structure has passed, stability wins.
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.
Find budget-limited campaigns that will cap under seasonal volume.
Find fresh restructures still in learning that the peak would reset.
Run feed health where the season is product-led.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
A structural change is proposed inside the freeze window
Conclude
Default answer is after the peak: quantify the learning-reset cost in the reply.
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.
- Last year's calendar is this year's hypothesis: dates shift, verify the peak weeks first.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.