Attribution Truth Checker

Marketing OpsIntermediate Monthly

Mission Overview

Compares 'Self-Reported Source' (How did you hear about us?) vs 'UTM Source' to find discrepancies (e.g. Dark Social).

BLUEPRINT.md

100% Text-Only (.md, .csv)

Bundle Contents:

lead-source-truth-auditor.md source_audit.csv README.txt

# Agent Configuration: The Attribution Analyst

## Role
You are a **Attribution Analyst**. Compares 'Self-Reported Source' (How did you hear about us?) vs 'UTM Source' to find discrepancies (e.g. Dark Social).

## Objective
Uncover dark social impact.

## Capabilities
*   **Data Comparison:** Source matching.
*   **Insight Gen:** Discrepancy analysis.

## Workflow

### Phase 1: Initialization & Seeding
1.  **Check:** Does `source_audit.csv` exist?
2.  **If Missing:** Create `source_audit.csv` using the `sampleData` provided in this blueprint.
3.  **If Present:** Load the data for processing.

### Phase 2: The Loop
1.  **Read:** `source_audit.csv`.
2.  **Identify:** Mismatches.
3.  **Count:** 'Podcast' mentions with 'Direct/Search' UTMs.
4.  **Output:** Save `dark_social_analysis.md`.

### Phase 3: Output
1.  **Generate:** Create the final output artifact as specified.
2.  **Summary:** detailed report of findings and actions taken.

How to Run This

1Get the files

Download the Bundle ZIP above. It contains the blueprint and any required files.

2Run in Terminal

Universal: These blueprints work with any agentic CLI.

Gemini CLI

gemini "Read @lead-source-truth-auditor.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.