Maximize Workflow Use
Workflows allow you to automate multi-step prompts, making complex interactions more structured and efficient. Unlike Agents, which function as single-prompt shortcuts, Workflows guide the AI through a sequence of prompts to ensure a more accurate and refined final response.
Creating a Workflow
1. Starting with a New Workflow
When you first access the workflow page, it will appear empty, indicating that there are no workflows set up yet. To create a new workflow, follow these steps:
Step 1: Create a New Workflow
Look for the "+ New Workflow" button. This button can be found in two places:
In the center of the screen, at the bottom of the page.
On the left sidebar, under the Workflow section.
Clicking this button will trigger the creation of a new workflow, and you will see a new card appear on the screen with the details of your first workflow step.
2. Workflow Execution Settings
At the bottom of the workflow area, you will find two key settings that control how the workflow behaves:
Execution Mode:
Human in the Loop: This mode requires the user to manually click a button to move to the next step after each one completes. This gives you control to review each step before proceeding.
Autopilot: In this mode, the workflow will automatically move from one step to the next without any manual input. This is ideal when you want the process to run automatically.
Workflow Trigger:
Manual: When set to manual, the workflow will only start when the user triggers it manually (by clicking a "play" button).
Automatic: In automatic mode, the workflow will begin as soon as certain actions occur, such as when a file is uploaded or when a message is received in the chat.
3. Saving or Cancelling the Workflow
Once you have configured the workflow to your liking, you can choose to either Save or Cancel your changes:
Save: Click the Save button to save the workflow you’ve just created or modified.
Cancel: If you wish to discard any changes and not save the workflow, click Cancel.
Editing the Workflow Card
1. Editing the Workflow Card Name
Name: The name of the step is typically descriptive of the task you want the AI to perform. For example, it could be something like "Step 1: Analyze", "Step 1: Gather Information", or "List down key points". This helps you quickly identify the purpose of that particular step in your workflow.
2. Step Type Selection
The Step Type field determines what kind of task this card will execute. There are several options, but for now, let’s focus on the most common one: Prompt.
Prompt: This step type allows you to provide a detailed instruction to the AI. The AI will use this instruction to carry out the task.
Other step types might include Integration and Variable, but these require different configurations. For this tutorial, we’ll focus on the Prompt type, which is the most commonly used when working with AI models.
3. Selecting the AI Model
Model: After selecting Prompt as the step type, you will need to choose a Model.
The model is essential because different AI models are better suited for specific types of tasks. For example, some models may excel at creative writing, while others are optimized for data analysis or technical tasks.
In this section, you’ll see a list of available models. For example, GPT 4 Omni is listed here, but you can select any other model that fits your task.
4. Writing the Instruction
Instruction: This is where you detail the task for the AI. It’s important to be as specific and clear as possible so the AI knows exactly what to do.
For example: “Please analyze the provided content thoroughly and transform it into a professional, well-organized document. Ensure that the text is clear, concise, and structured logically, with smooth transitions between ideas. Your task is to refine the language to maintain a formal tone that is appropriate for a business audience, using precise and authoritative language throughout. If any concepts or details are unclear, expand on them with relevant information or data to ensure full clarity. The final version should be suitable for internal reports, presentations, or formal communication with stakeholders.”
The clearer and more detailed your instruction, the more accurately the AI will be able to execute the task.
5. Web Research Option
Web Research: This toggle allows the AI to search the internet for relevant information to assist in completing the task.
If you enable this toggle, the AI will gather data from the web, which can be useful when the AI needs up-to-date or specific information that may not be readily available in the data room (the conversation thread).
If you don’t need web data, simply leave this toggle off.
6. Data Room Selection
Data Room: The Data Room is where the AI pulls information from to generate the result for this step.
What is a Data Room? It refers to the conversation thread that has been built so far. This includes the context and data exchanged in the current session. In other words, it’s the accumulated information and dialogue that the AI will use to produce the output for this specific task.
The data room ensures that the AI has access to all relevant information from previous steps or messages in the workflow.
Key Features Recap:
Name: Descriptive title for the task.
Step Type: Choose Prompt for tasks requiring instructions to the AI.
Model: Select the AI model that is most suited for the task.
Instruction: Provide detailed guidance for the AI on what to do.
Web Research: Toggle on if you want the AI to search the internet for additional data.
Data Room: Use the conversation thread (data room) as context for the task.
By following these instructions, you can effectively customize and configure each card in your workflow to meet your specific needs.
Starting a Workflow
Select your desired workflow from the list
Click the Play icon ▶️ to the right of the workflow
The workflow will run automatically
Workflow Progress
After starting, a process visualization appears in the bottom right corner of your screen:
Current step: Marked with a loading icon ⚙️
Completed steps: Highlighted in green ✅
Pending steps: Shown in neutral state
This visualization allows you to track the workflow's progress in real-time.
Last updated
