# Apple — Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs

- Company: Apple (apple.com)
- Announced: 2026-09-16
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://machinelearning.apple.com/research/glyph-column-description-tagging
- Record: https://forck.live/items/11441-glyph-a-multi-strategy-agentic-system-for-column-description-and-sensitivity
- Subject: Machine Learning Research

Apple researchers present Glyph, a production system using cooperating LLM agents to automatically generate column descriptions and assign data classification labels to enterprise data catalog tables. The system combines multiple strategies including retrieval-augmented generation from source code, description-based tagging, regex matching, and a fine-tuned metadata encoder, fusing results with Reciprocal Rank Fusion to improve classification accuracy.

## Evidence

Verbatim from https://machinelearning.apple.com/research/glyph-column-description-tagging:

> We present Glyph, a production system that frames two coupled problems, column description generation and column type annotation for data classification, as cooperating LLM agents orchestrated as stateful graphs.

---

Record: https://forck.live/items/11441-glyph-a-multi-strategy-agentic-system-for-column-description-and-sensitivity
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md