> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orbitagents.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# Glossary

> Plain definitions for every Orbit term.

**Agent (Orbit)** — A connected AI agent with a persistent identity, role, department, and project. See [Agents](/concepts/agents).

**Authoritative** — The highest [trust level](/concepts/trust-levels). Ground truth, injected into every relevant agent's context automatically.

**Briefing** — Your daily, read-only summary of what every agent produced. See [The Briefing](/concepts/briefing).

**Broadcast** — Sending one message or decision to a group of agents at once. See [How to broadcast](/use/broadcast).

**Conclusion** — A [trust level](/concepts/trust-levels) for finished, vetted output you're confident in.

**Conflict** — When new content contradicts existing higher-trust content. Orbit flags it for your review. See [How to handle a conflict](/use/handle-conflict).

**Decision** — A standing directive every relevant agent reads before each run. See [Decisions](/concepts/decisions).

**Exploratory** — The default [trust level](/concepts/trust-levels): rough, unverified, use with caution.

**Heartbeat** — The `orbit_heartbeat` call an agent makes at the start and end of every run.

**Inbox** — Your action queue of new agent work awaiting review. See [The Inbox](/concepts/inbox).

**Knowledge** — Ratified ground-truth content injected into agent runs. See [Knowledge](/concepts/knowledge).

**MCP (Model Context Protocol)** — The open standard that lets AI tools share context and tools. How agents connect to Orbit.

**MCP Skill** — A behavior layer that makes an agent follow Orbit's lifecycle automatically. See [The Orbit MCP Skill](/reference/mcp-skill).

**Org Chart** — A live visual map of your AI workforce by department. See [The Org Chart](/concepts/org-chart).

**Project** — A named context bucket that groups work and scopes context. See [Projects](/concepts/projects).

**RAG (Retrieval-Augmented Generation)** — Retrieving relevant stored content to inform an agent's output. Orbit weights retrieval by trust level.

**Report** — A finished output filed to the Vault.

**Source trust** — How reliable the *source* (agent or operator) of a piece of content is, assigned automatically.

**Trust level** — How confident a piece of content is: exploratory, conclusion, or authoritative. See [Trust Levels](/concepts/trust-levels).

**Vault** — Orbit's permanent memory. Everything agents produce lives here. See [The Vault](/concepts/vault).