> For the complete documentation index, see [llms.txt](https://docs-conversational-ai.syntphony.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs-conversational-ai.syntphony.com/studio/workspace.md).
# Workspace
Design, connect, and manage your NLU and AI Agent flows in a visual workspace.
## Overview
The **Workspace** is the visual environment where conversational flows are designed and managed in Syntphony CAI.
Depending on your project's governance, you can use the Workspace to manage **NLU flows**, such as Welcome, Not Expected, Jump, and User Journey flows, as well as **AI Agent flows**.
Flows are built by connecting **cells**, which define the sequence and logic of each conversational experience.
**Learn more about** [**Flows**](/studio/flows.md)\
**Learn more about** [**AI Agent Flows**](/studio/ai-agents.md)
Workspace Page
***
## Build a flow
Each flow starts from an **entry point**, which depends on the flow type:
* **AI Agent flow:** starts with the corresponding **AI Agent**.
* **User Journey flow:** starts with an **Intent**, as it is an NLU flow.
* **Welcome, Not Expected, and Jump flows:** the starting cell can vary depending on the conversational design and use case.
From the entry point, build the flow by adding and connecting Cells. Select **Add cell (+)** to add the next step:
* **Sequentially:** continues the current path.
* **As a sibling:** creates an additional branch from the same point.
This allows you to build both linear and branched conversational experiences.
***
## Add cells
When adding a cell, Syntphony CAI displays the Cell types available for that point in the flow.
They are organized into two groups:
* **Cells:** basic components used to build the main conversational flow.
* **Advanced:** components for more complex logic, integrations, input handling, and AI capabilities.
The available cells depend on the flow and the position where they are being added.
**Learn more about** [**Dialog Cells**](/build-dialogs/dialog-cells.md)\
**Learn more about** [**Workspace Cells**](/build-dialogs/workspace-cells.md)
***
## Create or reuse a cell
Depending on the Cell type, you can either:
* **Create a new Cell** specifically for your flow.
* **Select from the list** to reuse an existing Cell from its repository.
When you create a new repository-based Cell from the Workspace, it is automatically saved to its corresponding **Repository** and can be reused in other compatible flows.
{% hint style="info" %}
**Important:** Some cells belong to repositories and can be reused across flows, while others exist only within the Workspace. Their management and behavior may differ.
{% endhint %}
***
## Manage cells
Hover over a Cell to access the actions available for it:
* **Add:** add the next Cell or branch.
* **Edit:** review or update its configuration.
* **Remove:** remove the Cell from the flow.
When removing or restructuring Cells, some parts of the flow may become disconnected and need to be reconnected to an available endpoint.
{% hint style="info" %}
**Important:** Changes to a cell can affect other flows when the Cell is reused from a repository. Review its usage before making changes.
{% endhint %}
***
## Remove and reconnect cells
You can remove cells from a flow and reconnect the remaining structure directly in the Workspace.
When removing a Cell, choose whether to remove **only the selected Cell** or also its subsequent connected Cells. Removing only the selected Cell may leave parts of the flow disconnected.
To reconnect a flow:
1. Select an available connection point on the disconnected Cells.
2. The Workspace indicates which connections are valid.
3. Connect the compatible cells directly or add a new Cell between them when a direct connection is not supported.
{% hint style="info" %}
**Important:** Depending on the cell type and flow structure, some cells cannot be connected directly. In these cases, add a compatible cell between them to complete the flow.
{% endhint %}
After removing or reconnecting Cells, test the flow in **Dialog Simulator** to make sure all conversation paths continue as expected.
***
## Navigate the Workspace
The Workspace includes visualization controls to help you navigate flows of different sizes and complexity.
* **Full screen:** expands the Workspace for a larger working area.
* **Mini-map:** provides an overview of the flow and helps navigate large structures.
* **Fit to screen:** adjusts the view to display the entire flow.
* **Zoom:** increases or decreases the Workspace scale.
* **Collapse/expand:** hides or reveals subsequent parts of a flow to simplify visualization.
These controls do not change the flow behavior; they only affect how it is displayed in the Workspace.
***
## Test and monitor
You can test and inspect conversational behavior directly while working in the Workspace.
**Dialog Simulator** lets you run conversations and validate the flow from the end-user perspective.
**Log Viewer** provides execution information to help analyze behavior and troubleshoot issues.
**Learn more about** [**Dialog Simulator**](broken://pages/voLSONovKEGojmehUVDK)\
**Learn more about** [**Log Viewer**](broken://pages/ZWBBtnLlmK4oJlhMnagH)
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs-conversational-ai.syntphony.com/studio/workspace.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
