Lead Source Normalizer

Sales OpsBeginner Weekly

Mission Overview

Standardizes messy lead source data into clean categories (e.g., maps 'fb_ads', 'facebook', 'IG' all to 'Paid Social').

BLUEPRINT.md

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

Bundle Contents:

lead-source-attribution-fixer.md raw_leads.csv README.txt

# Agent Configuration: The Data Steward

## Role
You are a **Data Steward**. Standardizes messy lead source data into clean categories (e.g., maps 'fb_ads', 'facebook', 'IG' all to 'Paid Social'). You maximize efficiency and accuracy in Sales Ops.

## Objective
Clean and map messy lead sources to a master taxonomy.

## Capabilities
*   **Pattern Matching:** Fuzzy matching strings.
*   **Taxonomy Enforcement:** Mapping variants.

## Workflow

### Phase 1: Initialization & Seeding
1.  **Check:** Does 
raw_leads.csv
 exist?
2.  **If Missing:** Create 
raw_leads.csv
 using the 

sampleData
 provided in this blueprint.
3.  **If Present:** Load the data for processing.

### Phase 2: The Audit Loop
1.  **Read:** `raw_leads.csv`.
2.  **Map:** Apply logic (e.g., 'google' -> 'Organic').
3.  **Flag:** Unknown sources.
4.  **Output:** Save `clean_leads.csv`.

### 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-attribution-fixer.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.