Glossary
Definitions of every term used in Fruxon docs
A quick reference for the vocabulary in these docs and the product.
Agent
A configured AI workflow with prompts, steps, tools, knowledge, providers, and revisions. The unit of work in Fruxon. See Agents.
Agent Step
A node in an agent's flow that calls an LLM with a templated prompt, optionally using tools. The basic unit of work inside an agent.
API Key
An organization-scoped token for server-to-server access. Sent via X-API-KEY header. See Settings.
Asset
A file or data source attached to an agent for retrieval or templating. PDFs, DOCX, Confluence pages, GitHub repos, web URLs. See Knowledge Base.
Audit Log
Organization-level record of who did what when — deploys, member changes, integration changes, secret changes. See Security.
Baseline (Evaluation)
The reference revision (usually the deployed one) that a candidate revision is compared against during an evaluation run.
Budget
A per-agent monthly cost cap with alert thresholds. See Cost & Budgets.
Candidate (Evaluation)
The revision being tested in an evaluation run, scored against the baseline.
Chat User
An end-user who interacts with an agent through a connector. Identified by the connector's user identity (Slack user, phone number, email).
Code Executor
A built-in tool that runs Python in a secure sandbox. Useful for transforms, charts, calculations.
Connector
An inbound channel that delivers end-user messages to an agent — Slack, Teams, Telegram, WhatsApp, Discord, web. See Connectors.
Conversation
A multi-turn session with an end-user, sharing memory and session state across runs. See Conversations.
Dataset (Evaluation)
A list of test cases — inputs with optional expected outputs and metadata — used to score agent revisions. See Evaluations.
Deployed Revision
The revision currently serving production traffic for an agent. Switch instantly by deploying a different revision. See Versioning.
Entry Point
The starting node of every agent flow. Defines the typed inputs the agent accepts.
Execution / Run
One execution of an agent. Produces a trace.
Execution History
The log of all runs for an agent, filterable and searchable. See Monitoring.
Exit Point
The terminal node of every agent flow. Shapes the output returned to the caller.
Firebase JWT
The web app's user authentication token. Carries the organization claim. Used for human users; API keys are used for server-to-server.
Flow
The graph of nodes inside an agent. Designed visually in Studio.
Golden Dataset
A curated dataset of test cases used as a quality benchmark for evaluations.
Integration
A configured connection to an external service (Salesforce, PostgreSQL, etc.). Exposes one or more tools to agents. See Integrations.
Judge
An LLM that scores evaluation outputs against your defined metrics.
Knowledge Base
The collection of assets and data sources attached to an agent for retrieval. See Assets.
LLM Provider
A vendor of large language models — OpenAI, Anthropic, Google, etc. Connect with your own API key. See AI Providers.
Memory
Per-agent persistent key-value storage. Read and written by the agent through tools. Survives across conversations. See Memory.
Metric (Evaluation)
A measure used to score outputs in an evaluation — correctness, faithfulness, format, tone, etc. See Evaluations.
Node
Any element in an agent flow — Entry Point, Agent Step, Exit Point, control nodes.
Onboarding (Connector Policy)
A connector access policy where new users must be approved before they can interact with the agent. See Access Requests.
OpenAPI Tool
An integration tool defined declaratively from an OpenAPI/Swagger spec — URL, method, parameters, auth.
Organization
The top-level container for everything you build — agents, integrations, secrets, members, billing. Fully isolated from other organizations. Sometimes called tenant in API contexts (the URL path uses {tenant}).
Parameter
A typed input to an agent (string, number, boolean, object, array). Defined on the Entry Point.
Placeholder
Template syntax for referencing data in prompts and tool configs: {{input.X}}, {{step.Y.output}}, {{secret.Z}}, {{asset.W}}.
Predefined Tool
A custom-coded integration tool (as opposed to declarative OpenAPI tools). Used when an integration needs complex C# logic.
Revision
An immutable snapshot of an agent created on every save. See Versioning.
Role
A team member's permission level in an organization — Admin, Editor, or Viewer. See Team & Roles.
Sandbox Mode
A constrained execution mode for integrations (especially databases) that restricts capabilities — typically read-only. See Sandbox Mode.
Secret
An encrypted value stored in the organization and referenced via {{secret.X}}. Used for API keys, OAuth tokens, integration credentials.
Session
The state of a multi-turn conversation, including conversational context and any session-scoped variables. Auto-summarized as it grows. See Sessions.
Skill
A reusable bundle of instructions, tools, and knowledge that adds expertise to an agent. See Tools & Skills.
Solution
A pre-built agent template you can clone into your organization as a starting point.
Studio
The visual canvas where every agent is designed and tested. See Agent Studio.
Sub-agent
An agent invoked as a tool by another agent. Enables composition and decomposition. See Sub-agents.
System Prompt
The instructional message sent to the LLM that establishes the assistant's behavior, tone, and constraints.
Tag
A label attached to runs or conversations for grouping and filtering.
Tool
Anything an agent can do beyond generating text — calling APIs, querying DBs, running code, invoking sub-agents, reading/writing memory. See Tools & Skills.
Trace
The full record of one agent run — inputs, prompts, tool calls, outputs, tokens, latency, errors. See Monitoring.
User Prompt
The user-side message in an LLM call, typically built from placeholders against the run's inputs.
Vectorization
The process of embedding text chunks for semantic retrieval. Applied to assets when added to a knowledge base.