> 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/workflow-builder.md). # Workflow Builder The **Workflow Builder**, referred to as the **Canvas**, is the central workspace for creating, configuring, testing, and managing workflows in EmpowerGPT. The Canvas provides a visual environment where you can add blocks, connect them together, configure their settings, and define how data moves through your workflow. Whether you are building a simple automation or a complex multi-step process, the Canvas provides all the tools you need to design and manage your workflow from one place. ### Canvas Overview The Workflow Builder consists of four main areas: 1. **Top Header** 2. **Left Control Panel** 3. **Test Execute** 4. **Canvas Tools** Each area provides controls for a different part of the workflow-building experience.
*** ### 1. Top Header The **Top Header** provides information about the current workflow and access to its primary management actions. #### Workflow Title Displays the name of the current workflow. Use a clear and descriptive title that makes it easy to identify the purpose of the workflow. The workflow title can be updated as your workflow evolves. #### Version & Status Displays information about the current **version** of the workflow and its **status**. Versions allow you to keep track of changes made to a workflow over time, while the status helps distinguish between workflows that are still being worked on and version that have been deployed. #### Share & Deploy The **Share** option allows you to make the workflow available to other users based on the available sharing settings. The **Deploy** option allows you to deploy a workflow version when it is ready for use. Deployments help ensure that users execute a defined version of the workflow while you continue making changes to the workflow on the Canvas. *** ### 2. Left Control Panel The **Left Control Panel** provides access to the components and tools used to build and manage your workflow. #### List of Blocks The **Blocks** section contains the available building blocks that can be added to the Canvas. Blocks are grouped according to their purpose, such as: * **Trigger Blocks** – Define how the workflow starts. * **Logic Blocks** – Add conditions and loops to control workflow execution. * **Agent Block** – Uses AI to process information and perform tasks. * **Output Block** – Defines the information returned by the workflow. * **Other Processing Blocks** – Perform specialized actions such as document processing. Add the required blocks to the Canvas and connect them to define the sequence in which the workflow should execute. #### Create with AI **Create with AI** helps you build a workflow using natural language. Describe the process you want to automate, and EmpowerGPT can assist in creating the initial workflow structure on the Canvas. You can then review, configure, and modify the generated workflow according to your requirements. #### Past Runs **Past Runs** provides access to previous executions of the workflow. Use this section to review how the workflow executed and inspect the results of previous runs. #### Past Versions / Deployments This section provides access to previous versions and deployments of the workflow. It allows you to review the workflow's history and understand how its configuration has changed across different versions. *** ### 3. Test Execute **Test Execute** allows you to run the workflow directly from the Workflow Builder before deploying it. When you test a workflow, EmpowerGPT executes the connected blocks according to the flow defined on the Canvas. Use Test Execute while building your workflow to: * Verify that blocks are configured correctly. * Check whether variables are passed correctly between blocks. * Review the output generated by individual steps. * Identify configuration or execution errors. * Validate the final workflow output. Testing your workflow before deployment helps ensure that it behaves as expected with real input data. *** ### 4. Canvas Tools The Canvas includes several tools that make it easier to navigate and organize workflows. #### Zoom In / Zoom Out Use the **Zoom In** and **Zoom Out** controls to adjust the Canvas view. Zoom out to get an overview of larger workflows or zoom in when configuring and reviewing individual blocks. #### Re-arrange The **Re-arrange** option automatically organizes blocks on the Canvas to create a cleaner and more readable workflow layout. This is particularly useful for larger workflows where blocks and connections may become difficult to follow. #### Undo / Redo Use **Undo** to reverse recent changes made on the Canvas and **Redo** to restore changes that were previously undone. These controls make it easier to experiment with workflow structures and correct accidental changes while building your workflow. --- # 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/workflow-builder.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.