> ## Documentation Index > Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt > Use this file to discover all available pages before exploring further. # Xpander Chat > Xpander Chat, chat.xpander.ai on xpander cloud or your own domain when self-hosted, is the interface to the agents that run on xpander: conversations, tasks, approvals and sharing, on one screen for the whole team. Xpander Chat is where the agents that run on xpander live, as opposed to a client on someone's laptop. On xpander's cloud it is [chat.xpander.ai](https://chat.xpander.ai), free to register; a Hybrid or Air-Gapped install serves the same app on your organization's own domain. It is one address for everyone in the organization. Team members use agents, assemble new ones and follow their work; admins additionally see the Settings that govern every agent, described on [Govern every agent](/run/govern). ## Agents and conversations The left column lists **Agents**: the agents shared with you, Omni (the built-in agent), and **New** to assemble one. Below it, **Conversations** are grouped under **Today**, **Last week** and **Older**, with **Show all** to expand a group. Filters narrow them by agent, by user (**All users** shows teammates' conversations you have access to), **Source** (where the run started), **Status** and **Date**. **Status** includes **Scheduled**, for runs that have not happened yet. **See all conversations** opens the full list. ## A conversation The header names the agent and the conversation, and shows who can see it: **Only you**, a group, or the organization, changed with **Manage access**. Several people can write in the same conversation; every message carries its author's name and every action is recorded under the person who asked for it. The composer shows the harness and model the next message will run on, for example `Claude Code · Fable 5.1`, and the permission mode: * **Full** runs every command the agent decides on. Only the agent's **gated commands** wait for approval. * **Gated** holds every shell command, file edit and web fetch for approval; reads, searches and skills that are not themselves gated run unheld. **Harness and model** opens the picker: the providers your organization enabled, with the number of models each offers, and every model listed with the harness it runs on. Switching keeps the conversation; the new harness receives the history. Which providers and models appear is set by admins under Settings > LLM settings. ## Tasks and the execution log Every run is recorded as a task. The task panel shows the **execution log**: a counter of steps and actions, then one row per action with its status and time, such as `WebFetch`, `WebSearch`, a skill call, a shell command or `Task output`. Failed steps are marked. A stop button ends the run. **Task Details** opens the summary: status, files created, token usage, cost and the final answer. **Task Manager** lists every task for an agent, filtered by **This agent**, **Date**, **Status** or **Source**, and searchable by title or id. See [Tasks](/use/agents/conversations#the-task-record). Task Details panel showing status, token count, execution log steps and the final result Task Manager panel listing an agent's recent tasks with filter chips and a search box ## Approvals When an agent reaches an action that needs sign-off, the conversation shows a card with the action, its parameters and who started the run, with **Approve** and **Decline**. **Settings > Approvals** lists everything waiting for you across all agents. Held runs wait four hours by default, then stop. See [Approvals](/use/approvals) and [Permissions and access](/use/agents/permissions). ## Results, live surfaces and sharing Files an agent creates are in its **Agent workspace**. **Make live** on a file turns it into a **live surface**: a page the agent keeps up to date on each run, listed on the agent's **Live surfaces** card. **Share** on a conversation offers the audience **Only you**, **Specific people or groups**, **Everyone at** your organization, or **Public**, and whether viewers may reply. Sharing the agent itself, with view, use or edit permission, is done from the agent's **Manage access**. Public links exist only if an admin allows them under **Settings > Sharing**. ## Omni, the built-in agent Omni is an agent that ships with xpander, one row in every organization's agent list. Ask it to find an agent or a skill, run a task, explain what a run did, or assemble a new agent from approved skills. It answers in Xpander Chat, in Slack, in Teams and by email, and it serves the MCP endpoint your own client connects to (see [Start here](/use)). It is one agent among yours, not a separate product. ## Search and settings **Search** (`⌘K`) sits at the top of every screen. The bell shows notifications, including approvals waiting for you. The gear opens **Settings**. An admin sees tabs grouped as: * Account: Profile, Notifications, My connections, Approvals, Custom theme * Workspace: Team, User groups, Channels, MCP registry, Runtime environments, Locations, Knowledge bases * AI configuration: LLM settings, Memories * Security: API keys, Vault, OIDC, Sharing, Audit logs * Billing: License and Usage, on a licensed installation These tabs are described on [Govern every agent](/run/govern).