Creative Fatigue Review

AI Agent Instructions

Use this Classifier via the SuperClassify API from server code, not browser playground automation.

Build a periodic review job over comparable campaign windows. Compute delivery, frequency and performance changes in code, then submit those observations with creative history and known confounders. Queue investigate for a marketer; request missing evidence otherwise. Do not equate elapsed time with fatigue or pause spend from this judgment alone.

Class: superclassify/creative-fatigue-review@1.0.0
Fetch setup as text: https://superclassify.com/skills/superclassify/SKILL.md
Contract (JSON): https://superclassify.com/v1/resolve?ref=superclassify%2Fcreative-fatigue-review%401.0.0

First-time API access

When the user asks to run or integrate this Class, explain its workflow and that live Jev runs use SuperClassify service credits. Public card descriptions can be read without an account. Reuse an existing account, credit balance and API key when available. Otherwise, guide the user through the official setup links below. The user completes sign-in and any credit purchase on the website, then saves the API key in their application’s server secrets as SUPERCLASSIFY_API_KEY—not in chat. A separate TypeSafe account or Jev key is not required for the SuperClassify API. Reading a link does not authorize a purchase or paid run.

1. Create an account or sign in
2. Add credits if needed
3. Create an API key

Investigate repetition

Analytics diagnostics: adequate comparable samples, unchanged audience/budget/landing page, sustained deterioration across repeated periods, rising repeat exposure and repeated comments that the same creative is appearing too often. No known tracking change.

Author expectation: {"review":"investigate"}

No issue observed

Analytics diagnostics: adequate stable measurement, same campaign conditions, results stable across periods and no repetition complaints.

Author expectation: {"review":"no_observed_issue"}

Confounded decline

Yesterday performance dropped after the targeting, budget and landing page all changed. Only six conversions observed. No comparable baseline supplied.

Author expectation: {"review":"insufficient_evidence"}