How to read the graph

Tags

The graph begins with Tags, which represent the final classification output of the AI Mesh as well as compliance and data attributes. You can think of Tags as the entry point for exploring the system.

To drill down, click a Tag node (circle) to uncover the full sequence of connections.

You can view how upstream nodes like Detector Groups, AI Classifiers, DLP Policies, and Summarisers feed into the final decision. Each node shows how its signals influence the classification, helping you trace, audit, and fine tune the AI Mesh.

Click RESTART to return to the AI mesh page (default view).

Detector Groups

Detectors assess both the file path and its contents using rule-based logic, such as regular expressions and keywords. They return a match when the content fits the defined patterns.

To drill down, click a Detector Group node (circle) to uncover the full sequence of connections.

Click RESTART to return to the AI mesh page (default view).

DLP Policy Groups

DLP policy groups represent organization specific rules or policies applied to your data. They define thresholds, exceptions, and handling requirements, such as blocking external sharing of HR files.

To drill down, click a DLP Classifier node (circle) to uncover the full sequence of connections.

Click RESTART to return to the AI mesh page (default view).

Light AI Classifiers

Light AI Classifiers analyze a documents' semantic content using lightweight AI methods such as CBOW (Continuous Bag of Words) and topic modeling. These techniques identify themes like “Finance,” “HR,” or “Legal” even when sensitive terms are not explicitly mentioned, adding contextual understanding beyond simple keyword matching.

To drill down, click a Light AI Classifier node (circle) to uncover the full sequence of connections.

Click RESTART to return to the AI mesh page (default view).

AI Classifiers

AI classifiers use machine learning models trained on public datasets to detect content or categorize files. They move beyond simple keyword matching by evaluating context, patterns, and subtle signals helping identify complex or high risk data that rule based methods may overlook.

To drill down, click a AI Classifier node (circle) to uncover the full sequence of connections.

Click RESTART to return to the AI mesh page (default view).

Summarisers

Summarisers do not analyze raw content directly. Instead, they combine and consolidate signals from upstream detectors and classifiers to produce a unified, higher level insight.

To drill down, click a Summariser node (circle) to uncover the full sequence of connections.

Click RESTART to return to the AI mesh page (default view).