Skip to main content

​
Overview

Nebuly provides an advanced user intelligence layer that automatically analyzes your LLM interactions to reveal user intent, friction points, and satisfaction levels out of the box. However, while the platform can semantically interpret conversation transcripts, it lacks the organizational context required to drive strategic business decisions. With external metadata, distinguishing whether a “frustrated” user is a high-value premium customer, or whether a specific drop-off pattern is localized to a certain department or geographic region, becomes straightforward. This is why Nebuly’s tagging capabilities are essential for moving from individual session tracking to organizational intelligence.
By adding the right tags, you can create behavioral archetypes (e.g., Power Users vs. Skeptics) and track the adoption lifecycle across your organization or customer base.
Tag KeyExample ValuesUse Case
departmentengineering, legal, financeROI reports, risk segmentation
rolemanager, analyst, engineerAdoption lifecycle tracking
regionus-west, emea, apacGeographic segmentation
planpremium, starter, enterpriseCustomer value analysis
user_typepower_user, new_userBehavioral archetypes
Alt text

​
Where Tags Appear in Nebuly

Once tags are ingested, they populate several key areas within the platform.

​
Advanced Filtering and Segmentation

Tags become immediately available as filters throughout the Nebuly UI and reports. This allows you to slice your data and focus on, for example, only “Finance” department interactions where users expressed frustration.

​
ROI & Hours-Saved Reports

By tagging interactions with a department or role, Nebuly can calculate a specific business case for AI adoption. For instance, you can view a report showing that the “Engineering” department saved 450 hours in a given month, while “Legal” saved only 20 — signaling a need for better legal-specific training or enablement.

​
Risk & Compliance Alerts

Tags allow security teams to identify departmental risk variance. If the platform detects a spike in PII exposure, tags help pinpoint whether the issue is restricted to a specific team or time period (e.g., hiring season), enabling targeted intervention.

​
Technical Implementation

Tagging is handled via the Interaction API, specifically through the trace_interaction endpoint. Metadata is sent as a tags object consisting of key-value pairs associated with a specific interaction. 
{
  "interaction": {
    "tags": {
      "department": "engineering",
      "role": "senior_engineer",
      "region": "us-west"
    }
  }
}

Interaction API

See the full Interaction API reference for implementation details.