> 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/flows.md).

# Flows

Build structured conversational paths using cells and predefined flow logic.

## Overview

**Flows** are structured conversational paths built by connecting **Cells** in the Workspace. Depending on the flow, they can use Intents and Entities to recognize user needs, collect information, execute logic, integrate with external services, and deliver responses.

Syntphony CAI provides four types of Flows:

<table><thead><tr><th width="175.236083984375">Flow type</th><th>Purpose</th></tr></thead><tbody><tr><td>Welcome</td><td>Defines the initial conversational experience and can be used as a proactive greeting for supported channels.</td></tr><tr><td>Not Expected</td><td>Handles user inputs that are not recognized by the NLU layer.</td></tr><tr><td>User Journey</td><td>Defines a structured journey triggered by an <strong>Intent</strong> and designed to handle a specific user need.</td></tr><tr><td>Jump</td><td>Creates reusable flows that can be called from other conversational flows, helping avoid duplicated logic.</td></tr></tbody></table>

***

## Flows and governance

Flows are available across Syntphony CAI governance models, but the flows you can create depend on the selected **Governance**.

In projects using **Agentic-only Governance**, you can create only:

* **Welcome**, which can be used to configure a proactive channel greeting
* **Jump**, which can provide reusable flow logic for **AI Agent Flows**.

**Not Expected** and **User Journey** are available when the project's Governance includes the NLU layer.

**Learn more about** [<mark style="color:blue;">**Governance**</mark>](https://docs-conversational-ai.syntphony.com/project/governance-types.md)

***

## Build conversational flows

Flows are stored and managed in the **Flows repository** and visually designed in the **Workspace**.

A flow is built by connecting different types of Cells. Some Cells are reusable components stored in their respective **Repositories**, while others are configured directly within the Workspace.&#x20;

**Learn more about** [<mark style="color:blue;">**Workspace**</mark>](https://docs-conversational-ai.syntphony.com/studio/workspace.md)\
**Learn more about** [<mark style="color:blue;">**Dialog Cells**</mark>](https://docs-conversational-ai.syntphony.com/build-dialogs/dialog-cells.md)\
**Learn more about** [<mark style="color:blue;">**Workspace Cells**</mark>](https://docs-conversational-ai.syntphony.com/build-dialogs/workspace-cells.md)

***

## Train and test flows

When the project is integrated with an **NLP engine**, training is required to apply the latest NLU configurations and enable the engine to recognize the configured conversational elements.

After training, use **NLU Tests** to evaluate recognition results and validate whether user inputs are interpreted as expected.

Use **Dialog Simulator** to test the complete conversational experience, including flow execution and responses.

**Learn more about** [**NLU Training**](https://docs-conversational-ai.syntphony.com/project/governance-types.md#nlu-flows)\
**Learn more about** [**NLU Tests**](https://docs-conversational-ai.syntphony.com/project/governance-types.md#nlu-flows)\
**Learn more about** [**Dialog Simulator**](https://docs-conversational-ai.syntphony.com/training-and-testing/dialog-simulator.md)

{% hint style="info" %}
**Important:** If your project is integrated with an **NLP engine**, remember to train it after making relevant NLU configuration changes so they are reflected in recognition.
{% endhint %}


---

# 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/flows.md?ask=<question>&goal=<user_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.
