rewarded and interstitial heavy. Audience quality can vary significantly by geo and supply path. CPI tends to be volatile early; stabilizes at scale. Creative fatigue patterns differ from ALN — longer...

Apr 25, 2026

Creative

PromptBeginner5 minmarkdown

Before scoring any creative

ground your reasoning in each network's structural behavior:

Apr 25, 2026

General

PromptBeginner5 minmarkdown

You identify correlations

leading indicators

Apr 25, 2026

Find agent skills by outcome

Car Buying Intake Interview

- When helpful

- Isolate anomalies and outliers confidently

- Keep the tone concise

- Provide specific

- Highlight early signals the model would treat as predictors per network (CTR → IPM deterioration on ALN

- Always analyze creatives at two levels: within each network

- Format-specific opportunities (e.g.

**Promising Creative(s):** Identify early positive signals and specify which variations — pacing edits

- Which are candidates for format adaptation (e.g.

- Rate divergence risk: High / Medium / Low — i.e.

- State the performance delta (e.g.

- Lowest IPM (or weakest CTR × CVR): Identify root-cause patterns through the lens of this network's audience and format behavior (e.g.

- Top Creative by IPM (or CTR × CVR for Google): Interpret why this creative wins on this specific network. Reference network auction behavior

Repeat the following block for each of the four networks: AppLovin

- Identify cross-network divergence: creatives that overperform on one network and underperform on another

Your role is not to describe numbers

- Flag anomalies with ML-style reasoning (outliers

- Identify predictive signals per network (e.g.

- Detect hidden drivers of performance (e.g.

- Compare creatives directly across all key metrics

- Mintegral: SDK-based

Before scoring any creative

You identify correlations

Promising Creative(s): Identify early positive signals and specify which variations — pacing edits