Retail analytics context file

Use this example context file to streamline and scale your analytics workflows with Maia, Matillion’s agentic AI assistant. It’s designed to help retail analysts uncover insights faster by leveraging data from Matillion-prepared sources such as POS systems, e-commerce platforms, marketing campaigns, and inventory databases.

This file helps you move beyond manual reporting by enabling natural language queries, automating campaign impact analysis, and surfacing anomalies in store and product performance.

What’s inside the context file?

This sample file provides a reusable, editable template to support Maia-powered retail analytics. It includes:

  • Sample data source definitions for Snowflake and Google Sheets.

  • Best practices for naming conventions, schema design, and pipeline modularity.

  • Preconfigured agent tools for:

    • Conversational KPI queries
    • Marketing ROI analysis
    • Scenario modeling
    • Trend alerts

  • Sample logic and prompt behavior for use cases such as:

    • Sales and inventory correlation
    • Loyalty tier analysis
    • Campaign performance insights

You can adapt the file by replacing sample metadata and logic with your own standards. Save the updated version to your .matillion/maia/rules/ directory—Maia will automatically apply your settings when you interact with it.

How to use

  1. Download the sample file below.
  2. Replace placeholder logic, metadata, and KPIs with your own retail standards.
  3. Save it to your project’s .matillion/maia/rules/ directory.
  4. Maia will automatically apply these configurations during pipeline generation or prompt responses.

🔗 Learn how to use context files in Maia

📥 Download

Download the sample context file**

Use this template to build smart, scalable analytics workflows tailored to retail teams working in Matillion.

Target agentic AI enhancement for retail analyst

  • Enable natural language queries against Matillion-prepared retail datasets
    e.g., “Show me the top-selling products in the Northeast region last quarter.”

  • Automate “what-if” scenario analysis using Matillion’s transformation logic
    e.g., “What would be the impact on revenue if we applied a 15% discount to the ‘footwear’ category?”

  • Automate the creation and distribution of operational reports
    e.g., daily sales summaries, weekly inventory turnover—triggered directly via Matillion jobs.

  • Proactively identify significant trends or anomalies in retail metrics
    e.g., sudden dip in store traffic, spike in online cart abandonment.

  • Suggest relevant views or visualizations based on user questions
    e.g., sales heatmaps, conversion funnels, or SKU-level breakdowns from Matillion-transformed data.