In this step-by-step guide, we’ll show you how to create a production-ready Power Automate data extraction workflow for PDFs to Excel in just four simple steps. We'll use Cradl AI’s accurate AI OCR (optical character recognition) model to extract key information from any PDF with minimal effort. Then, we’ll push the data to Power Automate, where it can be used in hundreds of other apps, such as Excel.
Software Engineer
Before we begin, make sure you’ve created a free Cradl AI account.
Once you’re logged into Cradl AI, create your first AI model with just a few clicks. In this example, I’ll clone the Invoice model to keep things simple, but creating a model from scratch works just as well for other documents.
Customize the model to suit your needs by adding or removing fields based on the data you want to extract from your PDFs.
Why not take your new AI model for a spin to make sure it accurately extracts data from your PDFs? In Cradl AI, simply click on Run to upload documents, and the AI will automatically process them.
With your AI model ready to go, it’s time to create the destination for your extracted data: an empty Excel sheet.
Make sure your sheet is stored in a cloud file management service that integrates with Power Automate, like Microsoft OneDrive or Google Drive.
Add headers to your sheet that match the fields in your AI model. Take an extra moment to select your columns and format them as a table. This ensures everything runs smoothly when Power Automate adds rows to your sheet.
Now that your Excel sheet is ready, it’s time to connect Power Automate to it.
Start by creating an Instant Cloud Flow in Power Automate. Set the trigger to activate whenever an HTTP request is received.
Since the goal is to send extracted data as rows to your Excel table, use the “Add a Row to an Excel table” action. This step ensures that each piece of extracted data will appear neatly in your sheet.
Finally, let’s connect Cradl AI to Power Automate so the data extraction flow seamlessly converts PDF to Excel.
In Cradl AI, select Power Automate as your export destination. Cradl AI will auto-generate a JSON schema based on your model’s fields. Copy this schema and paste it into Power Automate.
Grab the Webhook URL from Power Automate and paste it into Cradl AI. Be sure to set the “Who Can Trigger The Flow” option to “Anyone.” Finally, revisit the “Add a Row to an Excel table” action in Power Automate and map the headers in your spreadsheet to the corresponding fields from Cradl AI.
In Cradl AI, hit Run, upload your documents, and let the system process them. Review the extracted data in Cradl AI’s Validator tool to fix any errors flagged by the AI.
Click Validate, and the entire flow—from Cradl AI to Power Automate to Excel—will run automatically.
By following these four simple steps, you’ve set up a production-ready workflow for automated PDF data extraction. With Cradl AI’s accurate and reliable models, you can extract key information from any document layout and seamlessly integrate it with Power Automate and Excel. This streamlined process not only eliminates the hassle of manual data entry but also makes document automation faster, safer, and incredibly easy.
If you would like a version of this tutorial that does into more detail, this video has got you covered.
We’ll help get you started with your document automation journey.
Schedule a free demo with our team today!
Internal document processing on autopilot.
