Glossary - Langfuse
Glossary
This glossary provides definitions for key terms and concepts used throughout the Langfuse documentation. Use the filters below to browse by category or search for specific terms.
Filter: Observability, Evaluation, Prompts, SDK, Platform, API
A
Agent
(Observation Type)
An observation type that represents an AI agent workflow, including multi-step reasoning processes, tool orchestration, and autonomous decision-making. Used to track agent behavior and interactions.
Related: Observation · Tool · Agent Graph · Span
Agent Graph
Observability
A visual representation of complex AI agent workflows in Langfuse. Agent graphs help you understand and debug multi-step reasoning processes and agent interactions by displaying the flow of observations within a trace.
Related: Trace · Observation · Agent · Span
Agentic Access
Platform
Ways for AI agents to work with Langfuse data and workflows programmatically, via the Langfuse Agent Skill, CLI, or MCP server, across observability, evaluation, and prompt management.
Related: MCP Server · Public API · SDK · Langfuse CLI
AI Engineering Loop
Observability, Evaluation
A lifecycle for continuously improving AI-powered systems by connecting production visibility with development workflows. It moves from tracing and monitoring real behavior to building datasets, running experiments, and evaluating changes before the cycle starts again.
Related: Trace · LLM-as-a-Judge · Dataset · Evaluator
Annotation Queue
Evaluation
A manual evaluation method that allows domain experts to review and add scores and comments to traces, observations, or sessions. Useful for building ground truth, systematic labeling, and team collaboration.
Related: Score · Trace · Session · Online Evaluation
API Key
Platform, API
Credentials used to authenticate with the Langfuse API and SDKs. API keys consist of a public key and secret key and are associated with a specific project. They are managed in project settings.
Related: Project · Public API · SDK
B
Billable Unit
Platform
The unit of measurement for Langfuse Cloud pricing. Units are the sum of traces, observations, and scores ingested per billing period.
Related: Trace · Observation · Score
C
Chain
(Observation Type)
An observation type that represents a link between different application steps, such as passing context from a retriever to an LLM call.
Related: Observation · Span · Retriever · Generation
Chat Prompt
(Message Prompt)
A prompt type that consists of an array of messages with specific roles (system, user, assistant). Useful for managing complete conversation structures and chat history.
Related: Text Prompt · Prompt Management · Prompt Variables
Custom Dashboards
Observability
Flexible, self-service analytics dashboards that allow you to visualize and monitor metrics from your LLM application. Dashboards support multiple chart types, filtering, and multi-level aggregations.
Related: Score · Token · Pulse
D
Dataset
Evaluation
A collection of test cases (dataset items) used to test and benchmark LLM applications. Datasets contain inputs and optionally expected outputs for systematic testing.
Related: Dataset Item · Dataset Experiment · Offline Evaluation
Dataset Experiment
(Dataset Run, Experiment Run)
The execution of a dataset through your LLM application, producing outputs that can be evaluated. Links dataset items to their corresponding traces.
Related: Dataset · Dataset Item · Task · Score
Dataset Item
Evaluation
An individual test case within a dataset. Each item contains an input (the scenario to test) and optionally an expected output.
Related: Dataset · Dataset Experiment · Task
E
Embedding
(Observation Type)
An observation type that represents a call to an LLM to generate embeddings. Can include model information, token usage, and costs.
Related: Observation · Generation · Retriever · Token
Environment
Observability
A way to organize traces, observations, and scores from different deployment contexts (e.g., production, staging, development). Helps keep data separate while using the same project.
Related: Project · Trace · Tags
Evaluation Method
Evaluation
A function that scores traces, observations, sessions, or dataset runs. Methods include LLM-as-a-Judge for subjective assessments, Annotation Queues for human review, Scores via UI for spot checks, and Scores via API/SDK for programmatic evaluation.
Related: Score · LLM-as-a-Judge · Annotation Queue · Dataset Experiment
Evaluator
(Scorer, Grader, Judge)
An observation type that represents functions assessing the relevance, correctness, or helpfulness of LLM outputs. Also refers to the function that scores experiment results.
Related: Score · LLM-as-a-Judge · Observation · Evaluation Method
Event
(Observation Type)
A basic observation type used to track discrete events in a trace. Events are the building blocks of tracing.
Related: Observation · Span · Trace
F
Filter Search Bar
Observability
A single-line query bar for filtering and searching the Observations and Traces tables by typing field:value expressions instead of assembling filters in the sidebar. Supports operators, wildcards, negation, and an Ask AI button that drafts filters from a plain-language description.
Related: Trace · Observation · Tags · Environment
Flush
SDK
The process of sending buffered trace data to the Langfuse server. Important for short-lived applications to ensure no data is lost when the process terminates.
Related: SDK · Trace · Instrumentation
G
Generation
(Observation Type)
An observation type that logs outputs from AI models including prompts, completions, token usage, and costs. The most common observation type for LLM calls.
Related: Observation · Token · Span
Guardrail
(Observation Type)
An observation type that represents a component protecting against malicious content, jailbreaks, or other security risks.
Related: Observation · Trace · Agent
I
Instance Switcher
Platform
A self-hosted Enterprise Edition feature that lists your Langfuse deployments (e.g. development, staging, production) in the sidebar user menu so you can switch between them without keeping URLs elsewhere. Mirrors the region switcher on Langfuse Cloud.
Related: Organization · Project
Instrumentation
SDK, Observability
The process of adding code to record application behavior. Langfuse provides context managers, observe wrappers, and manual observation methods for instrumenting your application.
Related: SDK · Trace · Observation · Flush
L
Langfuse Assistant
Platform
An in-product AI assistant, available on Langfuse Cloud, for exploring project data and Langfuse workflows in plain language. It queries traces, observations, sessions, and metrics through the Langfuse MCP server, searches documentation, and proposes navigation actions that you confirm.
Related: MCP Server · Trace · Observation · Session
Langfuse CLI
API, Platform
A command-line tool that wraps the Langfuse Public API, letting you manage prompts, evaluators, datasets, and other resources from the terminal or from AI coding agents. Supports pinning or auto-detecting a server's API version, so it works against self-hosted deployments running older releases.
Related: Public API · MCP Server · Agentic Access · SDK
LLM Connection
Platform
An API key configuration that allows Langfuse to call LLM models in the Playground or for LLM-as-a-Judge evaluations. Supports providers like OpenAI, Anthropic, and Google.
Related: Playground · LLM-as-a-Judge
LLM-as-a-Judge
Evaluation
An evaluation method that uses an LLM to score the output of your application based on custom criteria. Provides scalable, repeatable evaluations with chain-of-thought reasoning.
Related: Score · Evaluator · Online Evaluation · Offline Evaluation
Log View
Observability
Shows all observations concatenated. Great for quickly scanning through them.
Related: Agent Graph
M
MCP Server
Platform
A Model Context Protocol server that enables AI-powered tools to interact with Langfuse data. Used for advanced integrations and AI-assisted workflows.
Related: Public API · SDK · Langfuse CLI
Metrics API
API
An API endpoint for retrieving customized analytics from Langfuse data. Allows specifying dimensions, metrics, filters, and time granularity to build custom reports and dashboards for LLM applications.
Related: Custom Dashboards · Public API · Token
Model Definition
Observability
A configuration that stores pricing information for an LLM model. Model definitions specify the cost per input and output token, enabling Langfuse to automatically calculate the price of generations based on token usage.
Related: Token · Generation · Custom Dashboards
O
Observation
Observability
An individual step within a trace. Observations can be of different types (span, generation, event, tool, etc.) and can be nested to represent hierarchical workflows. Langfuse calls OpenTelemetry spans observations.
Related: Trace · Span · Generation · Event
Offline Evaluation
Evaluation
Testing your application against a fixed dataset before deployment. Used to validate changes and catch regressions during development.
Related: Dataset · Online Evaluation · Score · Dataset Experiment
Online Evaluation
Evaluation
Scoring live production traces to catch issues in real traffic. Helps identify edge cases and monitor application quality in production.
Related: Trace · Score · Offline Evaluation · LLM-as-a-Judge
OpenTelemetry
(OTel)
An open standard for collecting telemetry data from applications. Langfuse is built on OpenTelemetry, enabling interoperability and reducing vendor lock-in.
Related: Trace · Span · Instrumentation
Organization
Platform
A top-level entity in Langfuse that contains projects. Organizations manage billing, team members, and SSO configuration.
P
Playground
Prompts
The LLM Playground where you can test, iterate, and compare different prompts and models directly in Langfuse without writing code.
Related: Chat Prompt · Text Prompt · LLM Connection
Project
Platform
A container that groups all Langfuse data within an organization. Projects enable fine-grained role-based access control and separate data for different applications.
Related: Organization · RBAC · API Key · Environment
Prompt Label
Prompts
A label that can be assigned to a prompt version. Used to mark prompt versions as production or staging to fetch them via the SDK or API.
Related: Prompt Management · Protected Prompt Label
Prompt Management
Prompts
A systematic approach to storing, versioning, and retrieving prompts for LLM applications. Decouples prompt updates from code deployment.
Related: Chat Prompt · Text Prompt · Prompt Variables · Playground
Prompt Variables
Prompts
Placeholders in prompts that are dynamically filled at runtime. Allow creating reusable prompt templates with customizable content.
Related: Prompt Management · Chat Prompt · Text Prompt
Protected Prompt Label
Prompts
Restricts the ability to modify certain prompt labels (e.g. production) from being added to new prompt versions to admins and owners. This prevents accidental or unauthorized changes to production prompts.
Related: Prompt Management · Environment
Public API
API
The REST API that provides access to all Langfuse data and features. Used for custom integrations, workflows, and programmatic access.
Related: SDK · API Key · MCP Server · Langfuse CLI
Pulse
Observability
A compact outlier-chart strip above the Observations table that surfaces count, cost, and latency spikes over time. Clicking or dragging a spike narrows the table to that time window.
Related: Observation · Custom Dashboards
R
RBAC
(Role-Based Access Control)
Platform
Role-Based Access Control that manages permissions within Langfuse. Roles include Owner, Admin, Member, Viewer, and None, each with specific scopes.
Related: Organization · Project
Remote Experiment
Evaluation
A webhook-based trigger that allows running SDK experiments from the Langfuse UI. Configure a webhook URL and default config, then trigger experiments that fetch the dataset, run your application, and ingest scores back into Langfuse.
Related: Dataset · Dataset Experiment · Score
Retriever
(Observation Type)
An observation type that represents data retrieval steps, such as calls to vector stores or databases in RAG applications.
Related: Observation · Chain · Embedding
Rule
Evaluation
A configuration that selects incoming observations using filters and a sampling rate, then triggers one or more evaluators to score them.
Related: Evaluator · Observation · Online Evaluation · Score
S
Score
Evaluation
The output of an annotation or automated evaluation. Scores can be numeric, categorical, boolean, or text and are assigned to traces, observations, sessions, or dataset runs.
Related: Score Config · Evaluator · LLM-as-a-Judge · Annotation Queue
Score Config
Evaluation
A configuration defining how a score is calculated and interpreted. Includes data type, value constraints, and categories for standardized scoring.
Related: Score · LLM-as-a-Judge
SDK
(Software Development Kit)
SDK
Software Development Kit. Langfuse provides native SDKs for Python and JavaScript/TypeScript that handle tracing, prompt management, and API access.
Related: Instrumentation · Flush · Public API
Session
Observability
A way to group related traces that are part of the same user interaction. Commonly used for multi-turn conversations or chat threads.
Related: Trace · User Tracking
Span
(Observation Type)
An observation type that represents the duration of a unit of work in a trace. The default observation type for most operations. This is not a synonym for observation — OpenTelemetry spans become Langfuse observations of any type.
Related: Observation · Trace · Generation · OpenTelemetry
T
Tags
Observability
Flexible labels that categorize and filter traces and observations. Useful for organizing by feature, API endpoint, workflow, or other criteria.
Related: Trace · Environment
Task
Evaluation
A function definition that processes dataset items during an experiment. The task represents the application code you want to test.
Related: Dataset · Dataset Item · Dataset Experiment
Text Prompt
(String Prompt)
A prompt type that consists of a single string. Ideal for simple use cases or when you only need a system message.
Related: Chat Prompt · Prompt Management · Prompt Variables
Token
Observability
The basic unit of text that LLMs process. Tokens can be words, parts of words, or characters depending on the model's tokenizer. Token counts determine API costs and context window limits. Langfuse tracks input and output tokens for cost monitoring and optimization.
Related: Generation · Custom Dashboards
Tool
(Observation Type)
An observation type that represents a tool call in your application, such as calling a weather API or executing a database query.
Related: Observation · Agent · Span · Agent Graph
Trace
Observability
A single request or operation in your LLM application. Traces contain the overall input, output, and metadata, along with nested observations that capture each step.
Related: Observation · Session · Span · Generation
Tracing
Observability
The process of capturing structured logs of every request in your LLM application. Includes prompts, responses, token usage, latency, and any intermediate steps.
Related: Trace · Instrumentation · SDK
U
User Tracking
Observability
The ability to associate traces with users via a userId. Enables per-user analytics, cost tracking, and filtering.