# Workspaces A workspace enables you to create or connect to an AI agent and deploy it across multiple communication channels to manage interactions with customers. \ \ You can define team members for each workplace in order to manage chats, and also escalate chats from the AI agent to a human agent. Each workspace also consists of a team inbox where AI agent's output can be reviewed and managed. AI agents are deployed from our Agent store via our agent templates that can be configured by you to your own spec. Within the workspace, you can also set up a webchat widget for that can be installed on your website, or embedded on a page on your website, or social media page. It's also possible to connect the workspace with WhatsApp Business Platform, and in the future, other channels will be added. Only users at admin level are able to create a new workspace. You can define a workspace as a department (eg sales or support), a product (eg holiday rentals), a location (eg UK office) - basically anything you want! It's helpful to create a new workspace when you have distinct customers or clients to which you want to provide a more bespoke response to their inbound enquiry. A workspace can help uniquely identify the reason for the inbound request since the WhatsApp number or live chat widget can be associated with that particular product or location. This helps provide a more personalised response to the client or customer. Ideally workspaces should be deployed when it's unlikely for a customer to use two or more workspaces to access your services. In these circumstances, they will then need to store two (or more) sets of contact details, and this may be confusing. Contacts (described [here](/product-documentation/communications/contacts.md)) can be accessed from all workspaces. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://converso.gitbook.io/product-documentation/communications/workspaces.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.