# Dialogflow Detection Action

This action will parse any user text through Dialogflow engine. The conversation will not hold as a direct input. This action will trigger whenever the user text matches the configured intent.

![](/files/-LfOFzhQaEOHiypFqbUu)

### Settings

The action uses the following settings:

| Setting                      | Description                                                                                                                   | [Parsed](/actions-and-operations/dynamic-parsing.md) |
| ---------------------------- | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------- |
| API Version                  | Choose either V1 or V2, depending on the version of your Dialogflow Agent.                                                    | :no\_entry:                                          |
| API Access Token             | The API Token required to integrate your Version 1 Dialogflow Agent or the full Google Auth Json authorization file contents. | :white\_check\_mark:                                 |
| Project Id                   | The Dialogflow Project Id                                                                                                     | :white\_check\_mark:                                 |
| Language                     | The language of your agent. Make sure to select the same language you've configured on your agent.                            | :white\_check\_mark:                                 |
| Intent Name                  | The full name of the intent that will trigger this action. Use an asterisk (\*) to trigger on any intent                      | :white\_check\_mark:                                 |
| Detection Confidence         | The minimum confidence required to trigger this action                                                                        | :no\_entry:                                          |
| Display intent reply in chat | If enabled, Xenioo will display a message bubble witht the text you've specified as possible intent reply on Dialogflow.      | :no\_entry:                                          |

### Remarks

When used inside an [interaction](/basic-concepts/the-chatbot-designer/interactions_concepts.md) or [behavior](/basic-concepts/the-chatbot-designer/behaviours_concepts.md), this action **is not blocking.** The conversation is not halted and the user can continue freely. If you want to stop the user until the question requirements have been met, you can use the [Dialogflow Input action](/actions-and-operations/input/dialogflow/xenioo.bots.actions.dialogflow.dialogflowinputaction.md).

{% hint style="info" %}
Use \* (asterisk) in the Intent Name field to catch any DialogFlow intent instead of a specific one.
{% endhint %}

This action is optimized to use Dialogflow only once per user input. Even using multiple Dialogflow Detection actions will result in a single Dialogflow API Call. Every Dialogflow API call will count as an [additional chatbot message](/basic-concepts/your-account/messages-count.md#integrations).

The Language field is [fully parsed](/actions-and-operations/dynamic-parsing.md) to be dynamic so you can set your Dialogflow language dynamically at runtime. 

Any integration issue that Xenioo encounters during Dialogflow calls can be found inside each conversation [Execution Diagram](/actions-and-operations/execution/execution-diagram.md) or inside the chatbot preview [Execution Diagram](/actions-and-operations/execution/execution-diagram.md).

### Trigger

On Intent Detected. This action will trigger any child operation as soon as the user input is matching the selected intent with at least the specified confidence.

### Variables

This action produces the following variables after being triggered:

| Variable             | Description                             |
| -------------------- | --------------------------------------- |
| df\_detected\_action | The action detected during last input   |
| df\_detected\_intent | The intent detected during last input   |
| df\_reply            | The intent reply received by Dialogflow |

Every [entity](/ai/entities.md) specified in the detected [expression ](/ai/expressions.md)will be translated to a runtime variable named after the entity name.

### Availability

Channel specific availability follows the table below:

| Channel          | Availability                                                           |
| ---------------- | ---------------------------------------------------------------------- |
| Facebook         | Fully Available.                                                       |
| WhatsApp         | Fully Available.                                                       |
| Telegram         | Fully Available.                                                       |
| Web              | Fully Available.                                                       |
| Alexa            | **Not Available. Out of AI Detection is not supported inside skills.** |
| Google Assistant | Fully Available.                                                       |
| Slack            | Fully Available.                                                       |
| API              | Fully Available.                                                       |

This action can be used only at [Bot Global level](/actions-and-operations/execution.md#global-and-local-actions) or [Behavior level.](/actions-and-operations/execution.md#global-and-local-actions) This action is available only to [Premium Accounts](/basic-concepts/your-account/the-free-plan.md).


---

# 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://docs10.xenioo.com/actions-and-operations/input/dialogflow/xenioo.bots.actions.dialogflow.dialogflowdetectionaction.md?ask=<question>
```

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.