# Glossary

### Adaptive Analytics

The core mechanism for discovering, investigating, and tracking hidden behavioral signals from production AI log data. Adaptive Analytics continuously analyzes and updates the definition of "normal" behavior as new data becomes available, enabling deeper insights over time.

**Related Terms:** [Adaptive Analytics Flywheel](#adaptive-analytics-flywheel), [Behavioral Signals](#behavioral-signals)

**Learn More:** [Adaptive Analytics Workflow](https://docs.dbnl.com/v0.29.x/workflow/adaptive-analytics-workflow), [Overview](https://docs.dbnl.com/v0.29.x/get-started/readme#adaptive-analytics-flywheel)

### Adaptive Analytics Flywheel

The continuous 8-step cycle that powers DBNL's analysis: Ingest → Enrich → Analyze → Publish → Discover → Investigate → Track → Repeat. This flywheel adapts to previously tracked signals, providing deeper and more customized analytics over time.

**Related Terms:** [Data Pipeline](#data-pipeline), [Workflow](https://docs.dbnl.com/v0.29.x/workflow/adaptive-analytics-workflow)

**Learn More:** [Overview](https://docs.dbnl.com/v0.29.x/get-started/readme#adaptive-analytics-flywheel), [Adaptive Analytics Workflow](https://docs.dbnl.com/v0.29.x/workflow/adaptive-analytics-workflow)

### Analyze

The third step of the [Data Pipeline](#data-pipeline) where unsupervised learning and statistical techniques are applied to the distributional fingerprint to discover [Insights](#insights) such as behavioral changes, clusters, and outliers.

**Related Terms:** [Data Pipeline](#data-pipeline), [Insights](#insights), [Unsupervised Learning](#unsupervised-learning)

**Learn More:** [Data Pipeline](https://docs.dbnl.com/v0.29.x/configuration/data-pipeline), [Overview](https://docs.dbnl.com/v0.29.x/get-started/readme#adaptive-analytics-flywheel)

### Answer Relevancy

A default [LLM-as-Judge Metric](#llm-as-judge-metrics) that determines if the AI's output is relevant to the user's input. One of the core metrics computed automatically for every project.

**Related Terms:** [Default Metrics](#default-metrics), [LLM-as-Judge Metrics](#llm-as-judge-metrics)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#default-metrics), [LLM-as-Judge Templates](https://docs.dbnl.com/v0.29.x/workflow/metrics/llm-as-judge-metric-templates#llm_answer_relevancy)

### Behavioral Fingerprint

A statistical profile representing the expected behavior of an AI application, derived from distributions of historical data for each attribute. Also called a Distributional Fingerprint, it serves as a baseline to detect deviations and changes over time.

**Related Terms:** [Behavioral Signals](#behavioral-signals), [Model Drift](#model-drift)

**Learn More:** [FAQ](https://docs.dbnl.com/v0.29.x/reference/faq), [Adaptive Analytics](https://docs.dbnl.com/v0.29.x/workflow/adaptive-analytics-workflow)

### Behavioral Signals

Key insights or patterns extracted from AI production data that indicate specific behaviors. Signals can highlight daily shifts, clusters of similar behaviors, or outliers that deviate from the norm.

**Related Terms:** [Insights](#insights), [Adaptive Analytics](#adaptive-analytics), [Behavioral Fingerprint](#behavioral-fingerprint)

**Learn More:** [Insights](https://docs.dbnl.com/v0.29.x/workflow/insights), [FAQ](https://docs.dbnl.com/v0.29.x/reference/faq)

### Classifier Metric

A type of [LLM-as-Judge Metric](#llm-as-judge-metrics) that outputs a categorical value equal to one of a predefined set of classes. Example: `llm_answer_groundedness` outputs `grounded` or `not_grounded`.

**Related Terms:** [LLM-as-Judge Metrics](#llm-as-judge-metrics), [Scorer Metric](#scorer-metric)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#llm-as-judge-metrics), [LLM-as-Judge Templates](https://docs.dbnl.com/v0.29.x/workflow/metrics/llm-as-judge-metric-templates)

### Columns

Data fields extracted from logs and flattened according to the [DBNL Semantic Convention](#dbnl-semantic-convention). Required columns are: `input`, `output`, and `timestamp`.

**Related Terms:** [DBNL Semantic Convention](#dbnl-semantic-convention), [Logs](#logs)

**Learn More:** [Data Pipeline](https://docs.dbnl.com/v0.29.x/configuration/data-pipeline#columns), [DBNL Semantic Convention](https://docs.dbnl.com/v0.29.x/configuration/dbnl-semantic-convention)

### Dashboards

Collections of histograms, time series, and statistics of monitored [Columns](#columns), tracked [Segments](#segments), and generated [Metrics](#metrics) for user-driven analysis. DBNL includes three default dashboards: Monitoring, Segments, and Metrics.

**Related Terms:** [Metrics Dashboard](#metrics-dashboard), [Segments Dashboard](#segments-dashboard), [Monitoring Dashboard](#monitoring-dashboard)

**Learn More:** [Dashboards](https://docs.dbnl.com/v0.29.x/workflow/dashboards)

### Data Connections

The method by which production AI log data is ingested into DBNL, kickstarting the [Data Pipeline](#data-pipeline). Options include [OTEL Trace Ingestion](#otel-trace-ingestion), [SDK Log Ingestion](#sdk-log-ingestion), and [SQL Integration Ingestion](#sql-integration-ingestion).

**Related Terms:** [Data Pipeline](#data-pipeline), [Ingest](#ingest)

**Learn More:** [Data Connections](https://docs.dbnl.com/v0.29.x/configuration/data-connections)

### Data Pipeline

The process that converts raw production AI log data into actionable insights and dashboards. Consists of four key steps: [Ingest](#ingest), [Enrich](#enrich), [Analyze](#analyze), and [Publish](#publish).

**Related Terms:** [Adaptive Analytics Flywheel](#adaptive-analytics-flywheel), [Pipeline Run](#pipeline-run)

**Learn More:** [Data Pipeline](https://docs.dbnl.com/v0.29.x/configuration/data-pipeline), [Status](https://docs.dbnl.com/v0.29.x/workflow/status)

### DBNL Semantic Convention

A mapping from well-known formats into types and names that DBNL recognizes. Enables automatic and consistent data interpretation across different ingestion methods, including standard fields like `input`, `output`, `timestamp`, `model`, `total_token_count`, and `total_cost`.

**Related Terms:** [Columns](#columns), [Data Connections](#data-connections)

**Learn More:** [DBNL Semantic Convention](https://docs.dbnl.com/v0.29.x/configuration/dbnl-semantic-convention)

### Default Metrics

Built-in metrics computed automatically for every project using the required `input` and `output` fields and the default [Model Connection](#model-connections). Includes `answer_relevancy`, `user_frustration`, `topic`, `conversation_summary`, and `summary_embedding`.

**Related Terms:** [Metrics](#metrics), [LLM-as-Judge Metrics](#llm-as-judge-metrics)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#default-metrics)

### Deployment

A complete DBNL installation in a user's infrastructure, whether cloud VPC, on-premise, or sandbox environment. DBNL can be deployed using the Sandbox, Helm Chart, or Terraform Module.

**Related Terms:** [Sandbox](#sandbox), [Organization](#organization)

**Learn More:** [Deployment](https://docs.dbnl.com/v0.29.x/platform/deployment), [Architecture](https://docs.dbnl.com/v0.29.x/platform/architecture)

### Embeddings

Vector representations of text (like conversation summaries) used for semantic analysis and clustering. DBNL generates `summary_embedding` as a default immutable metric for topic generation.

**Related Terms:** [Topic Classification](#topic-classification), [Default Metrics](#default-metrics)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#default-metrics)

### Enrich

The second step of the [Data Pipeline](#data-pipeline) where data is augmented with [LLM-as-Judge](#llm-as-judge-metrics), NLP, and other behavioral [Metrics](#metrics) to create rich behavioral information vectors for every log.

**Related Terms:** [Data Pipeline](#data-pipeline), [Metrics](#metrics), [Model Connections](#model-connections)

**Learn More:** [Data Pipeline](https://docs.dbnl.com/v0.29.x/configuration/data-pipeline), [Overview](https://docs.dbnl.com/v0.29.x/get-started/readme#adaptive-analytics-flywheel)

### Explorer

A tool for rapid analysis and triage of [Segments](#segments) by performing graphical and statistical comparison between different subsets of [Logs](#logs) over time windows and/or filters. Supports Single Segment, Segment Comparison, and Temporal Comparison views.

**Related Terms:** [Segment Comparison](#segment-comparison), [Temporal Comparison](#temporal-comparison)

**Learn More:** [Explorer](https://docs.dbnl.com/v0.29.x/workflow/explorer)

### Ingest

The first step of the [Data Pipeline](#data-pipeline) where raw production log data is flattened into [Columns](#columns) using the [DBNL Semantic Convention](#dbnl-semantic-convention).

**Related Terms:** [Data Pipeline](#data-pipeline), [Data Connections](#data-connections)

**Learn More:** [Data Pipeline](https://docs.dbnl.com/v0.29.x/configuration/data-pipeline), [Overview](https://docs.dbnl.com/v0.29.x/get-started/readme#adaptive-analytics-flywheel)

### Insights

Human-readable explanations and quantifications of [Behavioral Signals](#behavioral-signals) generated from unsupervised analysis of enriched logs. Can be investigated through the [Explorer](#explorer) and tracked as [Metrics](#metrics) or [Segments](#segments). Three types: [Temporal Insights](#temporal-insights), [Segment Insights](#segment-insights), and [Outlier Insights](#outlier-insights).

**Related Terms:** [Behavioral Signals](#behavioral-signals), [Analyze](#analyze)

**Learn More:** [Insights](https://docs.dbnl.com/v0.29.x/workflow/insights)

### LLM-as-Judge Metrics

Evaluations that require an LLM to compute a score or classification based on a prompt. Includes [Scorer Metrics](#scorer-metric) (output 1-5) and [Classifier Metrics](#classifier-metric) (output predefined categories). Used for semantic understanding like relevance, tone, quality, and groundedness.

**Related Terms:** [Metrics](#metrics), [Model Connections](#model-connections), [Standard Metrics](#standard-metrics)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#llm-as-judge-metrics), [LLM-as-Judge Templates](https://docs.dbnl.com/v0.29.x/workflow/metrics/llm-as-judge-metric-templates)

### Logs

Individual records from production AI applications, displayed with filterable [Columns](#columns) and [Metrics](#metrics). Can be viewed in Detail, Trace, or Session views.

**Related Terms:** [Columns](#columns), [Session](#session), [Trace](#trace)

**Learn More:** [Logs](https://docs.dbnl.com/v0.29.x/workflow/logs)

### Metrics

A mapping from [Columns](#columns) into meaningful numeric values representing cost, quality, performance, or behavioral characteristics. Computed for every log as part of the [Data Pipeline](#data-pipeline). Two main types: [LLM-as-Judge Metrics](#llm-as-judge-metrics) and [Standard Metrics](#standard-metrics).

**Related Terms:** [LLM-as-Judge Metrics](#llm-as-judge-metrics), [Standard Metrics](#standard-metrics), [Default Metrics](#default-metrics)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics)

### Metrics Dashboard

Dashboard displaying all custom [Metrics](#metrics) as histograms (distribution), time series (daily trends), and statistics summaries for all logs within a specific time range.

**Related Terms:** [Dashboards](#dashboards), [Metrics](#metrics)

**Learn More:** [Dashboards](https://docs.dbnl.com/v0.29.x/workflow/dashboards#metrics-dashboard)

### Model Connections

How DBNL interfaces with LLMs for computing [LLM-as-Judge Metrics](#llm-as-judge-metrics), performing unsupervised analytics, and translating signals into human-readable [Insights](#insights). Supports providers like AWS Bedrock, Azure OpenAI, Google Vertex AI, OpenAI, and NVIDIA NIM.

**Related Terms:** [LLM-as-Judge Metrics](#llm-as-judge-metrics), [Enrich](#enrich)

**Learn More:** [Model Connections](https://docs.dbnl.com/v0.29.x/configuration/model-connections)

### Model Drift

When AI behavior deviates significantly from the established [Behavioral Fingerprint](#behavioral-fingerprint). DBNL detects drift through temporal analysis and alerts users to changes before they cause impact.

**Related Terms:** [Behavioral Fingerprint](#behavioral-fingerprint), [Temporal Insights](#temporal-insights)

**Learn More:** [FAQ](https://docs.dbnl.com/v0.29.x/reference/faq), [Insights](https://docs.dbnl.com/v0.29.x/workflow/insights)

### Monitoring Dashboard

Default dashboard displaying recommended graphs and statistics for a specific time window, including log counts, token usage, costs, and default metrics like `user_frustration` and `answer_relevancy`.

**Related Terms:** [Dashboards](#dashboards), [Default Metrics](#default-metrics)

**Learn More:** [Dashboards](https://docs.dbnl.com/v0.29.x/workflow/dashboards#monitoring-dashboard)

### Namespace

A unit of isolation within an [Organization](#organization) containing [Projects](#projects), [Data Connections](#data-connections), [Model Connections](#model-connections), and [Notification Connections](#notification-connections). Enables multi-tenancy and access control.

**Related Terms:** [Organization](#organization), [Projects](#projects)

**Learn More:** [Administration](https://docs.dbnl.com/v0.29.x/platform/administration#namespaces)

### Notification Connections

Integration channels (Email, Slack, PagerDuty) that inform users when specific DBNL actions are completed, such as data runs finishing or new [Insights](#insights) being generated.

**Related Terms:** [Projects](#projects), [Insights](#insights)

**Learn More:** [Notification Connections](https://docs.dbnl.com/v0.29.x/configuration/notification-connections)

### Organization

A DBNL [Deployment](#deployment) containing all [Namespaces](#namespace) and users for a single organization. The top-level entity in DBNL's hierarchy.

**Related Terms:** [Namespace](#namespace), [Deployment](#deployment), [Users](#users)

**Learn More:** [Administration](https://docs.dbnl.com/v0.29.x/platform/administration#organizations)

### OTEL Trace Ingestion

Publish OpenTelemetry (OTEL) traces directly to DBNL as the product runs. Enables the richest data with full trace inspection through [Spans](#spans) but doesn't support backfilling historical data.

**Related Terms:** [Data Connections](#data-connections), [Spans](#spans), [Trace](#trace)

**Learn More:** [OTEL Trace Ingestion](https://docs.dbnl.com/v0.29.x/configuration/data-connections/otel-trace-ingestion)

### Outlier Insights

Specific instances or sets of logs that deviate significantly from expected behavior related to one or more [Metrics](#metrics). Represents one of three types of [Insights](#insights).

**Related Terms:** [Insights](#insights), [Metrics](#metrics)

**Learn More:** [Insights](https://docs.dbnl.com/v0.29.x/workflow/insights#outlier-insights)

### Pipeline Run

An execution of the complete [Data Pipeline](#data-pipeline) for a specific date range, including Ingest, Enrich, Analyze, and Publish steps. Can be monitored and restarted from the [Status](#status) page.

**Related Terms:** [Data Pipeline](#data-pipeline), [Status](#status)

**Learn More:** [Status](https://docs.dbnl.com/v0.29.x/workflow/status), [Data Pipeline](https://docs.dbnl.com/v0.29.x/configuration/data-pipeline)

### Projects

The main organizational tool in DBNL; typically one project per AI application to analyze. Contains [Data Connections](#data-connections), [Model Connections](#model-connections), [Logs](#logs), [Metrics](#metrics), [Segments](#segments), and [Insights](#insights).

**Related Terms:** [Namespace](#namespace), [Data Pipeline](#data-pipeline)

**Learn More:** [Projects](https://docs.dbnl.com/v0.29.x/workflow/projects)

### Publish

The fourth step of the [Data Pipeline](#data-pipeline) where [Dashboards](#dashboards) are updated and new [Insights](#insights) are generated to represent newly observed and discovered behavior from the latest production data.

**Related Terms:** [Data Pipeline](#data-pipeline), [Insights](#insights), [Dashboards](#dashboards)

**Learn More:** [Data Pipeline](https://docs.dbnl.com/v0.29.x/configuration/data-pipeline), [Overview](https://docs.dbnl.com/v0.29.x/get-started/readme#adaptive-analytics-flywheel)

### Query Language

DBNL's language for creating [Standard Metrics](#standard-metrics) using functions like `word_count`, `flesch_kincaid_grade`, `levenshtein`, `contains`, and more. Enables fast, deterministic calculations without requiring an LLM.

**Related Terms:** [Standard Metrics](#standard-metrics), [Query Functions](#query-functions)

**Learn More:** [Query Language](https://docs.dbnl.com/v0.29.x/reference/query-language), [Functions](https://docs.dbnl.com/v0.29.x/reference/query-language/functions)

### Query Functions

Built-in functions available in the [Query Language](#query-language) for creating [Standard Metrics](#standard-metrics). Includes text analysis (word\_count, character\_count), readability scores (flesch\_kincaid\_grade), string operations (contains, levenshtein), and more.

**Related Terms:** [Query Language](#query-language), [Standard Metrics](#standard-metrics)

**Learn More:** [Functions](https://docs.dbnl.com/v0.29.x/reference/query-language/functions)

### Roles

Permission levels assigned to [Users](#users) in DBNL. Options include Organization Admin (full access), Namespace Admin (manage specific namespaces), and Namespace Writer (create/edit within namespaces).

**Related Terms:** [Users](#users), [Namespace](#namespace), [Organization](#organization)

**Learn More:** [Administration](https://docs.dbnl.com/v0.29.x/platform/administration#roles)

### Sandbox

A self-contained Docker container that bundles all DBNL services and dependencies for local testing and development. Not suitable for production but ideal for POCs and learning DBNL.

**Related Terms:** [Deployment](#deployment)

**Learn More:** [Sandbox](https://docs.dbnl.com/v0.29.x/platform/deployment/sandbox), [Quickstart](https://docs.dbnl.com/v0.29.x/get-started/quickstart)

### Scorer Metric

A type of [LLM-as-Judge Metric](#llm-as-judge-metrics) that outputs an integer in the range \[1, 2, 3, 4, 5]. Example: `llm_text_frustration` scores user frustration from 1 (not frustrated) to 5 (very frustrated).

**Related Terms:** [LLM-as-Judge Metrics](#llm-as-judge-metrics), [Classifier Metric](#classifier-metric)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#llm-as-judge-metrics), [LLM-as-Judge Templates](https://docs.dbnl.com/v0.29.x/workflow/metrics/llm-as-judge-metric-templates)

### SDK Log Ingestion

Push data manually or as part of a daily orchestration job using the DBNL Python SDK. The most flexible ingestion method but requires code and external scheduling.

**Related Terms:** [Data Connections](#data-connections), [Python SDK](#python-sdk)

**Learn More:** [SDK Log Ingestion](https://docs.dbnl.com/v0.29.x/configuration/data-connections/sdk-log-ingestion), [Python SDK](https://github.com/dbnlAI/docs/blob/main/reference/python-sdk.md)

### Segment Comparison

An [Explorer](#explorer) view that compares two different filters on [Logs](#logs) across the same time window. Allows comparison of [Metrics](#metrics) between segments or between a segment and the rest of the log data.

**Related Terms:** [Explorer](#explorer), [Segments](#segments), [Temporal Comparison](#temporal-comparison)

**Learn More:** [Explorer](https://docs.dbnl.com/v0.29.x/workflow/explorer#segment-comparison)

### Segment Insights

Detected clusters related to filters on [Columns](#columns) that correspond to unique behavior patterns. Bifurcates log data based on specific conditions. One of three types of [Insights](#insights).

**Related Terms:** [Insights](#insights), [Segments](#segments)

**Learn More:** [Insights](https://docs.dbnl.com/v0.29.x/workflow/insights#segment-insights)

### Segments

Saved filters on log data corresponding to specific [Behavioral Signals](#behavioral-signals). Automatically computed and published to the [Segments Dashboard](#segments-dashboard); inform and adapt future analytics.

**Related Terms:** [Behavioral Signals](#behavioral-signals), [Segment Insights](#segment-insights)

**Learn More:** [Segments](https://docs.dbnl.com/v0.29.x/workflow/segments)

### Segments Dashboard

Dashboard displaying all tracked [Segments](#segments) as time series of daily counts (or ratios) for each segment within a specific time range.

**Related Terms:** [Dashboards](#dashboards), [Segments](#segments)

**Learn More:** [Dashboards](https://docs.dbnl.com/v0.29.x/workflow/dashboards#segments-dashboard)

### Session

A group of related logs identified by `session_id`. Allows viewing all associated logs for a given session together with their [Metrics](#metrics) in Session View.

**Related Terms:** [Logs](#logs), [Trace](#trace)

**Learn More:** [Logs](https://docs.dbnl.com/v0.29.x/workflow/logs), [DBNL Semantic Convention](https://docs.dbnl.com/v0.29.x/configuration/dbnl-semantic-convention)

### Spans

Individual trace segments with timing and latency information, including attributes, events, and status. Used in [OTEL Trace Ingestion](#otel-trace-ingestion) to provide detailed execution visibility.

**Related Terms:** [OTEL Trace Ingestion](#otel-trace-ingestion), [Trace](#trace)

**Learn More:** [DBNL Semantic Convention](https://docs.dbnl.com/v0.29.x/configuration/dbnl-semantic-convention), [Logs](https://docs.dbnl.com/v0.29.x/workflow/logs)

### SQL Integration Ingestion

Pull data from a SQL table (BigQuery, Databricks, Snowflake, Redshift) into DBNL on a schedule. Leverages existing data infrastructure with no code required but needs pre-flattened data.

**Related Terms:** [Data Connections](#data-connections)

**Learn More:** [SQL Integration Ingestion](https://docs.dbnl.com/v0.29.x/configuration/data-connections/sql-integration-ingestion)

### Standard Metrics

Functions that can be computed using non-LLM methods like NLP metrics, statistical operations, and [Query Language Functions](#query-functions). Faster and cheaper than [LLM-as-Judge Metrics](#llm-as-judge-metrics).

**Related Terms:** [Metrics](#metrics), [Query Language](#query-language), [LLM-as-Judge Metrics](#llm-as-judge-metrics)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#standard-metrics), [Query Language](https://docs.dbnl.com/v0.29.x/reference/query-language)

### Status

The Status page shows all ongoing and previous [Data Pipeline](#data-pipeline) runs for a project, including current status, errors, and the ability to restart failed runs. Displays expected pipeline duration based on log volume.

**Related Terms:** [Data Pipeline](#data-pipeline), [Pipeline Run](#pipeline-run)

**Learn More:** [Status](https://docs.dbnl.com/v0.29.x/workflow/status)

### Temporal Comparison

An [Explorer](#explorer) view that compares a single filter across two adjacent time windows. Allows before/after [Metric](#metrics) comparison for a given [Segment](#segments).

**Related Terms:** [Explorer](#explorer), [Temporal Insights](#temporal-insights), [Segment Comparison](#segment-comparison)

**Learn More:** [Explorer](https://docs.dbnl.com/v0.29.x/workflow/explorer#temporal-comparison)

### Temporal Insights

Detected changes or shifts in behavior related to one or more [Columns](#columns) over time, defined by a time split showing "before" and "after" within a time window. One of three types of [Insights](#insights).

**Related Terms:** [Insights](#insights), [Temporal Comparison](#temporal-comparison)

**Learn More:** [Insights](https://docs.dbnl.com/v0.29.x/workflow/insights#temporal-insights)

### Topic Classification

A default [LLM-as-Judge Metric](#llm-as-judge-metrics) that classifies conversations into topics based on `input` and `output`. Topics are automatically generated after 7 days of ingested data and can be manually adjusted.

**Related Terms:** [Default Metrics](#default-metrics), [Classifier Metric](#classifier-metric)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#default-metrics), [Topic Template](https://docs.dbnl.com/v0.29.x/workflow/metrics/llm-as-judge-metric-templates#topic)

### Trace

A waterfall view of latency and timing for individual [Spans](#spans) in a request. Only available if spans data is provided through [OTEL Trace Ingestion](#otel-trace-ingestion).

**Related Terms:** [Spans](#spans), [OTEL Trace Ingestion](#otel-trace-ingestion), [Logs](#logs)

**Learn More:** [Logs](https://docs.dbnl.com/v0.29.x/workflow/logs), [OTEL Trace Ingestion](https://docs.dbnl.com/v0.29.x/configuration/data-connections/otel-trace-ingestion)

### Unsupervised Learning

Automated machine learning techniques applied to enriched data to discover behavioral patterns without labeled training data. Used in the [Analyze](#analyze) step of the [Data Pipeline](#data-pipeline) to generate [Insights](#insights).

**Related Terms:** [Analyze](#analyze), [Insights](#insights), [Behavioral Signals](#behavioral-signals)

**Learn More:** [Data Pipeline](https://docs.dbnl.com/v0.29.x/configuration/data-pipeline), [FAQ](https://docs.dbnl.com/v0.29.x/reference/faq)

### User Frustration

A default [LLM-as-Judge Metric](#llm-as-judge-metrics) ([Scorer Metric](#scorer-metric)) that assesses the level of frustration in user input based on tone, word choice, and other properties. Scored from 1-5.

**Related Terms:** [Default Metrics](#default-metrics), [Scorer Metric](#scorer-metric)

**Learn More:** [Metrics](https://docs.dbnl.com/v0.29.x/workflow/metrics#default-metrics), [User Frustration Template](https://docs.dbnl.com/v0.29.x/workflow/metrics/llm-as-judge-metric-templates#llm_text_frustration)

### Users

Individuals with login credentials to an [Organization](#organization), defined by [Roles](#roles) and [Namespace](#namespace) permissions. Can be authenticated via username/password or OIDC.

**Related Terms:** [Organization](#organization), [Roles](#roles), [Namespace](#namespace)

**Learn More:** [Administration](https://docs.dbnl.com/v0.29.x/platform/administration#users), [Authentication](https://docs.dbnl.com/v0.29.x/platform/authentication)

### Python SDK

The DBNL Python SDK for programmatically interacting with the platform, including data ingestion, project management, and metric creation. Installed via `pip install dbnl`.

**Related Terms:** [SDK Log Ingestion](#sdk-log-ingestion), [CLI](#cli)

**Learn More:** [Python SDK](https://github.com/dbnlAI/docs/blob/main/reference/python-sdk.md), [SDK Log Ingestion](https://docs.dbnl.com/v0.29.x/configuration/data-connections/sdk-log-ingestion)

### CLI

The DBNL Command Line Interface for interacting with the platform from the command line. Primarily used for authentication and managing the [Sandbox](#sandbox) deployment. Installed alongside the [Python SDK](#python-sdk).

**Related Terms:** [Python SDK](#python-sdk), [Sandbox](#sandbox)

**Learn More:** [CLI](https://docs.dbnl.com/v0.29.x/reference/cli)