# Set-up Chatbot Workflows 1. To create a Wonderchat workflow, select the chatbot of your choice and click on **Edit Chatbot**\\

Select "edit chatbot" from the dropdown menu

2. Within the edit chatbot menu, click on the **Workflows** tab, and click on **Add New Workflow**\\

3. A new workflow will be added. You can first select the type of trigger for your workflow. Here, we will select the **When AI detects a condition** trigger, and set the trigger when **The user asks what clothes he should wear**

4. Now that we have defined the trigger for the workflow, we can define a series of actions to take. For this workflow, we want to first **Collect the location of the user,** so we can click on **Add your first action** and create a new custom field called **Location**

Create a custom field called **Location**

5. Now, lets call add an API action to get the weather of the user based on the location that they have given.

Add a **Get Weather API** call under **Integrations** from **Add Action**

6. Finally, we can recommend the user some clothes they can wear based on the weather of the location they are in by adding an **AI Chatbot response action**

Add a **Chatbot Response** action that is based on an **AI Prompt**

7. Now that we have created our workflow, we can test it out by clicking **Save** and asking the chatbot a question that will trigger the workflow in the chatbot preview on the right. Alternatively, you can click on the **Play** button of each workflow to preview the workflow without manually typing in something to trigger it

Testing our chatbot workflow in the preview chat window

--- # 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.wonderchat.io/setup-guides/adding-chatbot-workflows/set-up-chatbot-workflows.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.