> For the complete documentation index, see [llms.txt](https://docs.empowergpt.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.empowergpt.ai/workflows/getting-started-with-workflows.md).
# Getting Started with Workflows
In this guide, you will create your first workflow in EmpowerGPT.
We will build a simple **"File Summarization Workflow"** that allows a user to upload a file, uses an AI Agent to summarize its contents, and displays the generated summary as the workflow output.
The Workflow will contain three blocks:
1. Form Trigger
2. Agent Block
3. Output
By the end of this guide, you will have a working workflow that you can test by uploading your own file.
{% stepper %}
{% step %}
### Create a New Worklfow
1. Navigate to **Workflows** in EmpowerGPT and create a new workflow.
2. Give your workflow a name and description (Optional), for example: **File Summarizer**
3. The Workflow Builder (Canvas) will open, where you can add and connect blocks to define how your workflow should operate.
{% endstep %}
{% step %}
### Add a Form Trigger
1. Every workflow starts with a **Trigger Block**. The trigger determines how the workflow begins and what initial information is provided to it.
2. For this workflow, select the **Form Trigger** by grabbing the Form trigger from block menu and placing it on the canvas.
3. The Form Trigger allows you to create input fields that are presented to the user when the workflow is started.
4. Add a new field and configure it as:
* **Field Type:** File
* **Field Name:** File
* **Required:** Yes
5. This creates a file upload field that users can use to provide the document they want to summarize.
6. The uploaded file will also become available as a variable that can be used by subsequent blocks.
{% endstep %}
{% step %}
### Add an Agent Block
1. Next, add an **Agent Block** and connect the **Form Trigger** to it.
2. Hover and click on in the '+' icon on the trigger block and drop an Agent Block on the canvas.
3. The Agent Block uses AI to process information and perform a task based on the instructions you provide.
4. Configure the Agent with an instruction such as:
> **Model:** Select any LLM Model such as GPT-5.4
>
> **Prompt:** Summarize the provided file. Identify the main topics and key information, and provide a concise and easy-to-understand summary.
>
> Give reference to the uploaded file in the prompt by typing {{}} and selecting the file fromt he form trigger.
>
> **Knowledge:** Click on 'Add' button and select the file uploaded to make it part of the agent knowledge.
{% endstep %}
{% step %}
### Add an Output block
1. Finally, add an **Output Block** and connect the Agent to it.
2. The Output Block determines which information is returned to the user when the workflow finishes.
3. Add an output block and in the configuration write {{}} and select the agent output. The output block will now show the agent as output.
{% endstep %}
{% step %}
### Test the Workflow
1. Your first workflow is now ready to test.
2. Run the workflow by clicking 'Test Execute' button at the bottom.
3. A form will appear and upload a sample document using the file field created in the Form Trigger.
4. EmpowerGPT will execute each block in sequence:
1. The **Form Trigger** receives the uploaded file.
2. The **Agent Block** processes the file and generates a summary.
3. The **Output Block** displays the generated summary.
5. Review the result to make sure the Agent produces the type of summary you expect.
{% endstep %}
{% endstepper %}
### What's Next?
You have created your first EmpowerGPT workflow!
Although this example contains only three blocks, the same approach can be used to create much more powerful automations.
You can extend workflows by adding **Conditions and Loops**, processing documents with specialized blocks, connecting external applications, working with APIs and webhooks, or generating files such as Excel, Word, and PowerPoint documents.
Next, explore the **Workflow Fundamentals** to understand how blocks, variables, connections, and workflow execution work together.
---
# 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.empowergpt.ai/workflows/getting-started-with-workflows.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.
