Skip to content
  • There are no suggestions because the search field is empty.

How to Deploy and Manage the COA/PDF Extraction Tool

Enhance your understanding of supplier quality performance and save valuable time by automatically extracting data from incoming certificates of analysis or PDF's. 

This guide explains how to configure and use the COA (Certificate of Analysis)/ PDF Extraction Tool  in AlisQI.
By the end of this guide, you will be able to:
  • Automatically extract data from COA PDFs
  • Store results in structured fields
  • Standardize incoming quality data

This feature is available with an active subscription to the Incoming Goods Inspections within the Supplier Quality module.

In this article

Step by Step Deployment Checklist

STEP 1 - Template Deployment

Your CSM will deploy template "Incoming COAs" to create the analysis set, the selection list for extracted Products and the extraction workflow. Once deployed you will find it under Results > Deployed Template. (if you are unable to see it check permissions)

    1. Alternatively, You can also enable workflows for existing analysis sets, provided that all necessary descriptive fields are present. Refer to the previously mentioned template to ensure all required fields are included.

STEP 2 - Define Data

Define What You Want to Extract: What data do you want from your COAs?

The AI does not create fields for you.You must first define which data you want to extract, and create those fields in your analysis set.

Common examples:

  • Supplier
  • Product name
  • Batch / Lot number
  • Quantity
  • pH
  • Viscosity
  • Test Result (Pass/Fail)
  • Calibration date
  • Due date

STEP 3 - Edit Template

This feature demands minimal configuration. There's no necessity to manually map values from the COA to fields in the analysis set, as the application automatically attempts to align them.

Simply add the fields you wish to extract from the PDF document.

  1. Open and edit your COA analysis set (More > Analysis Set)

  2. Add fields for each value you want to extract for example: 

Important:
  • Field names should closely match what is written in your PDF
  • Use correct data/field types (text, number, date)
  • Remove fields you do not use

STEP 4 - User Set-up

Creating a dedicated ''User'' and ''User group'' for this function is key in allowing the AI to write the data back into AlisQI while eliminating any risk of mixed login information with an actual user.

It cannot be an existing User within AlisQI

    1. Create a new user group, to isolate permissions
      1. Go to Management → User Groups
      2. Click Add Group
      3. Name it: COA Extraction
    2. Create a new user account, so that API calls are properly traceable.
      1. Go to Management → Users
      2. Click Add User
      3. Fill in Username: coa_extraction
      4. Group: COA Extraction
      5. Admin: No

STEP 5 - User Permissions

Configure access and permissions for the new user group:

  1. Grant all permissions for the ''Incoming COAs'' analysis set
    (    Manage > Permissions  > Analysis set)
  2. Grant View and Manage permissions for the "Incoming COA | Product" selection list.
    (Manage > Permissions > Selections list)
  3. Grant access to the Specification Management feature in the Module access management.
    (Manage > Permissions > Module)

STEP 6 - Authentication Token

  1. Generate an API authentication token for this new user, give it an expressive name like "PDF COA Parser"

API authentication tokens can be managed from the Integration hub.

To create a new token, click the "+ Create new token".  A new panel appears.

In the panel, select a user account, provide a name and click save. 

     2.   Share the access token with your CSM or the Support Team.

STEP 7 - Upload and Extract Data

The team will confirm that the extraction tool has been activated internally you can now test and refine.

  1. Go to the COA set and select ''Add result''
  2. In the result entry screen attach your PDF/COA (only 1 attachment per result)
  3. Click Save to trigger the workflow and extraction process. 
    The workflow designed to initiate the extraction process. This workflow incorporates a reference to the setId and the tenant's subdomain (tenant.alisqi.com). It automatically activates when a new Result is generated with a single PDF attachment. Additionally, the workflow can be manually triggered,.
  4. Review the imported data in your result overview and verify accuracy

STEP 8 - Finetune and Refine

To improve the accuracy, there are variety of ways.

You can provide a set of custom instructions to provide more context or examples on how to extract the right values from the PDF document and modify your analysis set to suit your need

Read more on this article about how to finetune your Extraction Tool set up.

Limitations

Currently, we can extract values from COAs under the following conditions:

  1. The document must be a native PDF, as we do not utilize OCR for scanned images.
  2. Each document should contain only one lot or batch. We can process a single batch, lot, or delivery per document, with all data consolidated into one result in AlisQI.
  3. The COA/PDF may have one or multiple pages, provided all pages pertain to the same batch or delivery, allowing us to handle multiple pages effectively.

Best Practices

Start with 10–15 key fields
  1. Test with 5–10 sample PDFs
  2. Adjust field names and structure
  3. Standardize COA formats where possible
  4. Scale to full usage

Pro-Tips

  • Keep your setup simple first
  • Expand only after validation
  • Use consistent naming conventions
  • Regularly review extracted data quality

By following these steps and continuously refining your setup, you can ensure accurate and consistent data extraction from your COAs. A well-configured extraction tool not only saves time but also improves data reliability across your quality processes.