Document Intelligence

Extract structured data via natural language from uploaded documents and images

Feathery Document Intelligence automatically extracts structured data from your documents, either directly uploaded or automatically pulled from your system of record.

Document intelligence is available on the Business plan. Reach out to sales to get access.

Define document queries in an Extraction

Go to the AI tab of your form and click "Create New Extraction". Give your extraction a name and select the fields to pull files from for running your extraction. You can leave "Correct Image Rotation" turned off unless you expect many of your inputted documents/images to not be oriented correctly (ex: turned sideways, upside down, etc)

For each piece of data you want to extract from the document, you can add a new natural language query that tells Feathery AI what to extract. If no suitable value is found, the field will be left blank.

For each query, you can define the following components:

  1. Frequency: this is how many values you want to extract for a specific query.

    1. One Value returns a single value

    2. Multiple Values returns multiple values in a list (e.g. a list of all items purchased in this bank statement)

    3. Tabular Data is optimal for extracting relevant rows and columns from data you know will be formatted as a table in the document.

  2. Entity: the information you want to pull from the document (e.g. stock holding, account balance, etc.)

  3. Save To: which form or hidden field to save the extracted values to.

  4. Criteria (optional): additional details or constraints about the entity to be queried that allow Document Intelligence to fine-tune relevant data (e.g. only pull stocks purchased after 2020).

Upload or connect documents

You can have Document Intelligence run on files uploaded to your form or connect it to native Feathery integrations like Egnyte, S3, Google Drive, and more to automatically pull in new documents uploaded to specific storage destinations.

Connect Document Intelligence to your form

  1. Create a form with the following fields:

    1. A file upload field (at the beginning of the form)

    2. All the fields you want to extract from your documents

  2. In your form, add a button with the AI Document Extraction action and select the Extraction you just defined. Now, any files uploaded to this field and submitted by your users will automatically trigger the Extraction to run. You can also specify if you want your form fillers to wait until the extraction completes so the form populates with extracted data for review / update.

Review & approval

You can review extractions that are run in the AI tab by clicking on the Extraction we just defined. You can view the data pulled from each document that the extraction was run on and the location in the document where the data was found. You can also edit the extracted data if you find errors before approving the final result if you have reviewers defined for your extraction.

Configure Reviewers

If you don't set reviewers for your Extraction, runs will be auto-approved and subsequent actions (e.g. routing data) will be automatically triggered.

You can set reviewers for your Extraction in the configuration screen. The available reviewers are members of your Feathery team. Any configured reviewers will receive an email notification each time there's an available extraction to for them to review.

Reviewers will have access to an approval button on pending extraction runs to confirm the accuracy of the data.

Route and validate extracted data

Once extracted document data has been approved, it can be used in advanced logic or mapped to integrations that send the data in your desired format to relevant systems of record.

Last updated