Data analyst context file

Use this example context file to boost analytical productivity with Maia, Matillion’s agentic AI assistant. Designed specifically for data analysts, this file enables conversational access to prepared datasets, automates routine reporting, and detects performance anomalies—so you can focus on driving insights and business outcomes.

By combining Maia’s intelligence with Matillion’s transformation capabilities, your team can reduce time spent on wrangling data and increase time spent interpreting it.

What’s inside the context file?

This sample file provides a reusable template to support Maia-assisted workflows for data analysts. It includes:

  • Predefined access to analytical views prepared in Matillion (e.g., shipping, cost, and supplier performance)
  • Sample agent tools for:
    • Conversational KPI queries
    • Automated anomaly detection
    • Operational reporting with scheduled Matillion jobs
  • Natural language query translation logic
  • Example Matillion job orchestration for on-demand analysis
  • Use case logic for:
    • Delivery performance summaries
    • Cost comparison across suppliers and routes
    • Alerting on outlier values like spike in spoilage or delay times

You can tailor this file by updating job names, table structures, metrics, or report types to match your business needs. Save it to your .matillion/maia/rules/ directory and Maia will automatically apply these instructions when responding to analyst prompts.

How to use

  1. Download the sample file below.
  2. Replace placeholder metadata, datasets, and job names with your own project-specific standards.
  3. Save it to your project’s .matillion/maia/rules/ directory.
  4. Maia will automatically apply these practices when generating pipeline logic

🔗 Learn how to use context files in Maia

📥 Download

Download the sample context file

Use this template to enable AI-driven data analysis, reporting, and insight generation for Matillion users.

Target agentic AI enhancement for data analyst

  • Enable natural language queries against Matillion-prepared datasets
    e.g., “Show me average delivery times by region for last quarter.”

  • Automatically detect anomalies in key metrics like cost per shipment or spoilage rate
    e.g., “Alert me if delivery delays spike more than 2 standard deviations above baseline.”

  • Automate generation of recurring reports and dashboards
    e.g., weekly route efficiency summaries or daily supply chain health reports.

  • Provide dynamic answers to operational queries using real-time data
    e.g., “Which supplier had the highest delay rate this month?”

  • Suggest relevant visualizations or analyses based on context
    e.g., trends over time, comparisons across categories, or detailed anomaly breakdowns.