evidently-ai

Name: evidently-ai
Availability: InStock
Author: DTMC-marketplace

Monitor ML models in production for data drift and performance degradation.

2|Updated Jan 15, 2026

Search Tags:#mlops #compliance #data drift #model monitoring #ai act #evidently ai

Ready to run

npx skills add https://github.com/DTMC-marketplace/governance --skill evidently-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: evidently-ai
Source: https://github.com/DTMC-marketplace/governance/tree/main/skills/evidently-ai
Command: npx skills add https://github.com/DTMC-marketplace/governance --skill evidently-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the critical need to monitor Machine Learning models in production, detecting performance degradation and data drift to ensure ongoing accuracy and compliance.

Core Features & Use Cases

Production Model Monitoring: Track data drift, model performance, and target drift using visual reports.
Compliance Assessment: Evaluate AI systems against EU AI Act Article 15 requirements for assessment, implementation, documentation, and monitoring.
Risk Mitigation: Implement controls for performance risks and ensure AI systems remain reliable.
Use Case: A financial institution can use this skill to continuously monitor a fraud detection model for shifts in input data distributions or a decline in accuracy, triggering alerts for retraining or investigation.

Quick Start

Use the evidently-ai skill to assess the current compliance status of the AI system against Art. 15 requirements.

Frequently Asked Questions about evidently-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I monitor ML models in production for data drift and performance degradation?▼

You can monitor ML models in production for data drift and performance degradation by integrating the Evidently library into your deployment pipelines to generate visual reports and continuous oversight of model behavior.

What is data drift and when do I need to track it in machine learning pipelines?▼

Data drift occurs when input data distributions change in production. You need to track data drift when your ML models are deployed in production to ensure ongoing accuracy and mitigate performance risks.

Can I use Evidently AI to assess compliance against the EU AI Act?▼

Yes, you can use Evidently AI to assess compliance against EU AI Act Article 15 by evaluating the current state of your AI systems, implementing controls for performance risks, and documenting monitoring findings.

Do I need ML deployment pipelines to monitor model performance and target drift?▼

Yes, you need existing ML model deployment pipelines because continuous oversight requires integration with your deployed models to effectively monitor target drift, data drift, and performance degradation.

What is the best way to detect target drift in a fraud detection model?▼

The best way to detect target drift in a fraud detection model is to continuously monitor it using the Evidently library, which tracks shifts in input data distributions and triggers alerts for investigation or retraining.