Creating a Workflow

Getting Started with Creating Your First Workflow

Creating a workflow in AgenticFlow AI is a straightforward process. Follow these steps to get started:

Creating a Workflow

The easiest way to start creating a workflow is to navigate to the Workflows page. Once on the page, click on + Create Workflow at the top right corner.

You will be presented with an empty state where you can:

• Add knowledge

• Add inputs

• Add workflow actions

• Access some video tutorials

Add Knowledge

Knowledge is defined as any information that a language model might not already have. For instance, a chain of conversation in emails can be knowledge for a workflow scripting email responses.

Adding knowledge to a workflow is done by clicking on the + Add Knowledge button. AgenticFlow AI handles all the required steps, from storing the data to vectorizing specified fields; details are fully explained in the knowledge documentation.

Add Inputs

Every workflow has inputs. Inputs are used to pass data or instructions on how to analyze the data into the workflow.

Adding inputs to a workflow is done by clicking on the + Add Input button. AgenticFlow AI provides you with a variety of input types and handles all the required steps; details are fully explained in the User Inputs documentation.

Add Desired Actions

Actions are the analysis components of a workflow. The most frequently used action in AgenticFlow AI is LLM, which allows you to communicate with a Large Language Model (LLM) of your choice. However, it is not limited to that. AgenticFlow AI provides you with a variety of actions, from simple ones like API calls to more complex ones like vectorizing and knowledge search.

Adding analysis actions to a workflow is done by clicking on the + Add Action button. For more information on the available actions, visit the Workflow Actions documentation.

Example

Step-by-Step Guide to Creating a Simple Workflow

1. Add an Input:

   • On your new Workflow page, click on + Add Input and then select Text Input to add a new input that accepts short pieces of text. A Text Input component will now appear on the page.

   • Add a title (optional).

   • Add a description (optional).

   • Change the variable name, shown in green, from text to topic. Note that this variable name will be used further down in the guide.

2. Add a Workflow Action:

   • Click on + Add Action and then choose LLM from the available options. This will add an LLM component to the workflow.

   • We are going to experiment with text generation using LLMs such as GPT.

3. Configure the LLM Prompt:

   • Enter the text below in the Prompt section of the LLM component:

     Create an engaging Instagram caption based on the following: "{{topic}}"

   • Using {{}} and variable names, you can access the variables and their values.

4. Save and Run Your Workflow:

   • Hit Save at the top right corner.

   • Run your Workflow. You can either go to the Use tab or try it on the current page. Enter the text below in the user input component:

     AI is changing the way teams work

   • Click on Run Once (on the App page) or on the run icon (on the Build page) on the LLM action, and you will see the LLM output. For instance, the GPT-3.5 might generate:

     🚀 Embrace the future of teamwork! AI is revolutionizing the way teams collaborate, innovate, and achieve extraordinary results. Say goodbye to traditional work methods and hello to a whole new era of efficiency and creativity! 💡✨ #AIRevolution #TeamworkEvolved

By following these steps, you can quickly create and test your first workflow, leveraging the power of LLMs to automate and enhance your business processes.