FruxonDocs

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.

Token

An organization-scoped, scoped access token for server-to-server access — a personal access token (fx_pat_) or a service-account token (fx_sat_). Sent via the Authorization: Bearer header. See Tokens.

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

An organization-level record of sensitive credential activity — secret, token, and service-account events (who accessed or changed what, when). See Security.

Baseline (Evaluation)

The currently deployed revision, which a candidate revision is automatically 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.

Participant

A person, group, or AI agent that can address agents through one or more channels. See Agent Network.

Code Executor

A built-in tool that runs Python in a secure sandbox. Useful for transforms, charts, calculations.

Agent Network

Tenant-level wiring for triggers, participants, participant channels, conversations, and access requests around agents. See Agent Network.

Conversation

An observed provider thread or end-user session, such as a Slack channel, Telegram chat, Teams thread, or phone-number conversation. 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 Observability.

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; tokens 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 notes — each a title, body, and optional tags — searched by keyword. 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.

Access Request

A proposed participant or participant-agent binding raised when an unknown or unbound sender tries to address an 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, INTEGER, FLOAT, BOOLEAN, OPTION, JSON, STRING_ARRAY, DICTIONARY, ASSET, or TOOL. Defined on the Entry Point.

Placeholder

Template syntax for referencing data in prompts and tool configs: {{param.X}} (entry parameter), {{step.Y}} (a previous step's output), {{secret.Z}} (a secret), and <file:…> (an attached asset, inserted from the asset picker).

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 permission level. Organization roles are Owner, Admin, Developer, Operator, or Viewer; agent collaborator roles are Viewer, Editor, or Admin. Effective agent access requires both levels. 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. See Secrets.

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.

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 Observability.

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.

On this page