Use this example context file to streamline and scale your data quality practices with Maia, Matillion’s agentic AI assistant. It shows how a data quality engineer can embed validation rules, monitoring standards, and remediation logic directly into AI-powered workflows—ensuring Matillion pipelines meet enterprise-grade reliability.
What’s inside the context file?
This sample file includes:
- Agentic tools configured for detecting, reporting, and responding to quality issues.
- Embedded standards for:
- Schema conventions.
- Field-level validation.
- Pipeline-level data quality thresholds.
- Root cause diagnostics via Matillion metadata
Maia agentic instructions: Data quality engineer
- Proactive anomaly detection: Automatically detect and flag common issues in Matillion pipelines—like missing shipment IDs, out-of-range weights, duplicate rows, or inconsistent timestamp formats.
- Automated reporting: Generate standardized data quality reports using Matillion’s validation outputs, surfaced directly through Maia in natural language or tabular format.
- Root cause analysis: Analyze Matillion job logs, transformation history, and upstream data sources to suggest likely causes for quality degradation.
- Quality-triggered orchestration: Dynamically orchestrate cleansing, enrichment, or rerun jobs in Matillion when defined quality thresholds are breached.
How to use
- Download the sample file below.
- Replace placeholder rules, metadata, and logic with your organization’s standards
- Save it to your project’s
.matillion/maia/rules/directory. - Maia will automatically apply these instructions when generating or refining data pipelines
🔗 Learn how to use context files in Maia
📥 Download
Download the sample context file
Use this as a template to enable intelligent, standards-driven data quality management in your Matillion projects.