Ctrl+K

Introduction

1. Introduction

AI for Metadata Quality

2. Generative AI for Metadata Quality
3. Metadata Quality Assessment with LLM

Metadata Augmentation

4. Metadata Augmentation Methodology
5. Metadata Augmentation: Technical Details

Metadata Reviewer

6. Metadata Reviewer
7. Agentic AI Approach
8. Implementation of ai4data.metadata.reviewer

Data Discoverability

9. Data Discoverability

Model Context Protocol (MCP) for AI-centric Data Dissemination

10. Model Context Protocol (MCP) for AI-centric Data Dissemination

Monitoring of Data Use

11. Monitoring of Data Use

Anomaly Detection in Data

12. Anomaly Detection in Development Data
13. Anomaly Explanation Methodology Handbook
14. Motivation: Why LLM Elicitation for Anomaly Explanation
15. Elicitation Pipeline: How It Works
16. Reviewer Feedback System
17. Timeseries Anomaly Explanation with LLMs

Efficient and Inclusive AI Applications

18. Efficient and Inclusive AI Applications

Partnerships

19. Partnerships

Repository
Suggest edit
Open issue

.md

Partnerships

19. Partnerships#

Under development…

By Development Data Group

Last updated on Apr 13, 2026.

Country borders or names do not necessarily reflect the World Bank Group’s official position. All maps are for illustrative purposes and do not imply the expression of any opinion on the part of the World Bank, concerning the legal status of any country or territory or concerning the delimitation of frontiers or boundaries

All content (unless otherwise specified) is subject to the MIT License.