# Generative Journey® (Slots)

## **What's *****Generative Journey***** in slot capture mode?**

The *Generative Journey®* node is a powerful building block in your flow that brings a large language model (LLMs) into the process. In slot-capture mode, it's designed to gather multiple pieces of information (slots) from a user in a natural, conversational way. Instead of relying on rigid question-and-answer sequences, the LLM flexibly interprets how users provide details, as some users might give all information in one sentence, skip around, or provide answers out of order. This makes the experience more fluid and efficient, while reducing the number of separate nodes you need to build into a flow.

<figure><img src="/files/gTQwfzIudozEDd4T6mMl" alt=""><figcaption></figcaption></figure>

Imagine a customer uses your conversational app and says:\
\&#xNAN;*"I need a hotel in Boston this weekend."*

With slot-capture Generative Journey:

* A flow is invoked that is designed to handle hotel booking
* When the Generative Journey node is hit, the LLM recognizes and fills `location = Boston` and `dates = this weekend` without the user needing to explicitly answer a question
* It naturally asks follow-up questions like, *"How many people will be staying?"*
* It notices that other required slots (number of guests, room type, budget) are still missing
* It allows the user to answer in any order (e.g., *“It’s for two adults, and under $200 a night would be great”*)

Once all slots are collected, the node ejects from the Success path, and the resolved slot variables can be used to complete the rest of the workflow. All of this happens within one node, keeping the flow streamlined while still giving the user freedom to provide details conversationally.

***

## Checklist

You'll complete the following to successfully launch a workflow powered by Generative Journey in slot mode:

* [ ] Create flow
* [ ] Deploy
* [ ] Install

***

## Step 1: Create flow

{% hint style="success" %}
Est. time to complete: \~8 minutes
{% endhint %}

Begin by identifying the tasks your conversational AI application will automate and organize them into individual topics handled by [flows](/platform/nlx-platform-guide/flows-and-building-blocks/overview.md). Determine the sequence of steps and messaging that the conversational application follows to assist a user with the task. The conversation workflow is assembled in the Canvas builder with a pattern of nodes similar to a flow diagram.

Each flow is invoked when your chosen AI model identifies user intent from a user's utterance ("I want to order room service") and matches it to a flow you've created `OrderRoomService`. This match is done based on the training data you provide for your AI model.

* Select *Resources* from workspace menu > Choose *Flows* > Click *New flow*
* Enter a descriptive name (no spaces or special characters) > Select *Save*
* Complete [Flow setup](/platform/nlx-platform-guide/flows-and-building-blocks/overview/setup.md) by attaching training data and attaching slots
* Add nodes by right-clicking on the Canvas & choosing *New node* (see available [node types](/platform/nlx-platform-guide/flows-and-building-blocks/overview/nodes.md#node-types))
* Connect first node to *Start* node > Connect sequential nodes via node edges or stacking
* Add conversational AI messages to nodes by selecting *+ Add message* on a node's side panel
* Place a *Generative Journey* node on the Canvas
* Select *Slot capture*
* Provide a succinct prompt to the LLM on what flow the task is part of, the end goal of the task, specific messaging or branding requirements (if any), and things to avoid (if any)
* Assign all *Required slots* needed to complete the task
* Link from the node's *Success* edge to the next node in the flow
* Click *Save*

Repeat for any additional flows your application will help automate.

:brain: Looking for more? See [Intro to flows](/platform/nlx-platform-guide/flows-and-building-blocks/overview/flows-and-variables.md)

***

## Step 2: Deploy

{% hint style="success" %}
Est. time to complete: \~2 minutes
{% endhint %}

Now you'll create the conversational AI application users will interface with. This step involves attaching all flows you want your application to access, defining flows to handle certain behaviors, setting up the channels where your application will be installed, and deploying.

* Select *Applications* from workspace menu > Choose *New application*
* Click *Blank application* from the available options > Choose *Custom*
* Provide a name for your application > Click *Create application*
* On *Configuration* tab of application
  * Under *Functionality* section, attach one or more flows created in previous step to make available to your application > Click Save
  * Click <i class="fa-gear">:gear:</i> *Default behavior*  > Assign any attached flow to the application's behaviors
  * Under *Delivery* section, select the API channel > Turn on [*Streaming*](/platform/nlx-platform-guide/ai-applications/deployment/managing-channels/creating-an-api-channel.md) to send Generative Journey output token-by-token, so text renders and voice plays as it’s generated
  * Click *Save*

A build now constructs a package of your application with a snapshot of current state of flows, languages, and application setup. A deployment then pushes a successful build to the communication channels where your app is installed:

* Click deployment status in upper right > Select *Build and deploy*
  * Review [*Validation check*](#validation-check) for critical errors or detected UX issues in custom flows. Before each new build initiates, a validation check is run to provide a preview of potential errors that may cause failed builds. Detected issues are listed with descriptions and potential solutions
  * You may provide a *Description* of notable build edits as a changelog
  * Click *Create build*
* Click deployment status in upper right > Select *All builds* > Choose *Deploy* on successful build > Click *Create deployment*

***

## Step 3: Install

{% hint style="success" %}
Est. time to complete: \~5 minutes
{% endhint %}

* Click the *Configuration* tab of your application > Click any channel assigned in the *Delivery* section
  * For finalizing MCP, choose the API channel in your *Configuration* tab and choose *Setup instructions* tab to access how to set up your MCP Client (ensure you turned ON [*MCP interface*](#delivery) before building and deploying)
* Choose the *Setup instructions* tab and follow instructions for installing to your [chosen communication channel](/platform/nlx-platform-guide/ai-applications/deployment/managing-channels.md)

Once you deploy a build, you can use your application outside the NLX workspace in two ways:

1. *Delivery channel:* Interact with the app through the channel where it’s installed (e.g., web chat via API channel, voice, SMS, MCP Client)
2. *Touchpoint (hosted chat):* Open the hosting URL from the deployment details to chat with the app. Hosting must be enabled when you deploy

{% hint style="warning" %}
Want to take your app offline? Click the deployed build > Select *Deployment* tab in modal > Scroll to *Danger zone* and click *Delete* *deployment*. The app stays offline until you redeploy.
{% endhint %}


---

# 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://docs.nlx.ai/platform/nlx-platform-guide/flows-and-building-blocks/advanced/generative-journey-r-slots.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.