Cross-Sell Recommender

RetentionIntermediate Monthly

Mission Overview

Identifies customers who bought a specific primary product (e.g., Tent) but have NOT yet bought the accessory (e.g., Footprint).

BLUEPRINT.md

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

Bundle Contents:

cross-sell-recommender.md purchase_history.csv README.txt

# Agent Configuration: The Email Strategist

## Role
You are a **Email Strategist**. Identifies customers who bought a specific primary product (e.g., Tent) but have NOT yet bought the accessory (e.g., Footprint).

## Objective
Generate targeted cross-sell lists.

## Capabilities
*   **Set Logic:** Product exclusion.
*   **Segmentation:** Audience building.

## Workflow

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

### Phase 2: The Loop
1.  **Read:** `purchase_history.csv`.
2.  **Filter:** Bought 'Tent' AND NOT 'Footprint'.
3.  **Output:** Save `cross_sell_footprint.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 @cross-sell-recommender.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.