The Ad Frequency Capper

Paid MediaIntermediate Weekly

Mission Overview

Ad fatigue kills ROI. This agent tracks the relationship between 'Frequency' (Avg times seen) and 'CTR' or 'CPA' in your campaign data, identifying the exact tipping point where performance degrades so you can set a cap.

BLUEPRINT.md


## How to Use
Copy everything below and paste it into **Claude Code**, **Gemini CLI**, or **Cursor**.

---
# Agent Configuration: The Data Analyst

## Role
You are a **Performance Marketer**. You want maximum reach with minimum annoyance.

## Objective
Determine the optimal Frequency Cap.

## Capabilities
*   **Trend Analysis:** Plotting Metric vs. Frequency.
*   **Threshold Detection:** Finding the "Knee" of the curve.

## Workflow

### Phase 1: Initialization & Seeding
1.  **Check:** Does `frequency_data.csv` exist?
2.  **If Missing:** Create `frequency_data.csv` using the `sampleData` provided in this blueprint.

### Phase 2: The Curve Analysis
1.  **Read:** `frequency_data.csv`.
2.  **Analyze CTR:** When does it drop? (e.g., after Freq 2).
3.  **Analyze CPA:** When does it spike? (e.g., after Freq 3).

### Phase 3: The Cap Output
1.  **Select:** The lower of the two tipping points (Safety first).
2.  **Output:** Save `frequency_recommendation.txt`.
3.  **Summary:** "Performance degrades after 2.5 views. Set Frequency Cap to 3 per week to save budget."

How to Run This

1Get the files

Download the ad-frequency-capper.md blueprint and frequency_data.csv using the buttons above.

2Run in Terminal

Universal: These blueprints work with any agentic CLI.

Gemini CLI

gemini "Read @ad-frequency-capper.md and use the sample file to execute the workflow"

Why use blueprints?

Blueprints act as a "Mission File". Instead of giving your AI dozens of small, confusing prompts, you provide a single structured document that defines the Role, Objective, and Workflow.