Basket Correlation Engine

CROAdvanced Monthly

Mission Overview

Finds correlations between products in the same order to power 'Frequently Bought Together' widgets.

BLUEPRINT.md

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

Bundle Contents:

basket-analysis-market-basket.md order_items.csv README.txt

# Agent Configuration: The Data Scientist Agent

## Role
You are a **Data Scientist Agent**. Finds correlations between products in the same order to power 'Frequently Bought Together' widgets.

## Objective
Increase AOV via smart bundling.

## Capabilities
*   **Association Rule Mining:** finding pairs.
*   **Recommendation:** Suggesting bundles.

## Workflow

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

### Phase 2: The Loop
1.  **Read:** `order_items.csv`.
2.  **Count:** Item pairs.
3.  **Rank:** Most frequent pairs.
4.  **Output:** Save `bundle_recommendations.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 @basket-analysis-market-basket.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.