Articles on: Use-Cases

Use-Case: Smart Data Mapping with Conduit

Introduction



With Conduit, you can easily convert a chaotic array of digital documents into structured, actionable data. Whether it's extracting specific information from lengthy contracts or processing numerous invoices simultaneously, our platform's intelligent algorithms handle it with ease. This not only speeds up your workflow but also ensures a higher level of data accuracy and reliability.

Getting started with Conduit's Smart Document Processing



To begin, log into your Conduit account.

Navigate to the 'Workflows' tab. Here, you'll find the option to create a new workflow. Let's click on 'Create New Workflow'.

Let's begin by adding a ‘Pull CSV Import’ block to your canvas. This block would serve, as an entry point for the workflow. Then, drag and drop the ‘Ask AI’ block onto the canvas, connecting it to the Pull CSV block and configure the ‘Ask AI’ block:

Dataset Selection: Choose the dataset containing the digital documents.
Input Column: Select the column that contains the data you want to process. This is typically the column where your raw digital data is located.
Output Column: Specify the column where you want the processed data to be placed.

Make sure, that you've granted permissions for editing the sheet, prior to using it for saving the output

Specifying AI Tasks with Natural Language Commands



You have the flexibility to define precise instructions for the AI by crafting natural language commands, commonly referred to as prompts. In the following example, we'll attempt to map the order details to a sheet, which will be compromising of several columns

Here is the example order data:



Let's compose a prompt for extracting date & time of the order

Extract the date of the order from the text in the dataset. Just print the date of the order

Click on the 'Run Workflow' button to launch the Workflow. If everything were done correctly, you should receive a notification on the bottom right corner of the screen

Please do not modify the {value} parameter and bear in mind, that it would be necessary to keep it within your prompt

Mapping the multiple cells



For scenarios where your raw data includes diverse information that needs to be mapped to multiple sheets, Conduit provides a seamless solution. By incorporating multiple 'Ask AI' blocks into your workflow, you can efficiently process distinct elements of your raw data and direct them to various sheets. Each 'Ask AI' block acts as a specialized tool, enabling you to specify unique instructions for extracting specific details.

For example, if your raw data contains order details and customer information, you can add separate 'Ask AI' blocks to extract and map these distinct elements to their respective sheets. Simply repeat the process of configuring 'Ask AI' blocks tailored to your data's intricacies, offering a comprehensive approach to mapping multiple cells across different sheets.

Updated on: 19/01/2024

Was this article helpful?

Share your feedback

Cancel

Thank you!