To enable accurate and efficient data extraction from COAs, the AI Extraction Settings page must be properly configured. This setup ensures that the system can correctly identify suppliers and items while extracting relevant data based on predefined business rules.
How to Configure AI Extraction Settings
Step 1: Set COA Processing Defaults by completing the following:
- Go to Configuration > AI Settings.
- Set Use to 'COA' from the drop down menu.
- Ensure Automatic Data Processing is toggled OFF. This is recommended for initial implementation.
Step 2: Configure Supplier Identification Attributes by clicking Add Attribute.
- Supplier Email Attribute: To ensure accurate AI extraction, select an attribute that reflects the email domain from which the COA is received. The attribute type can be either Email or Text for flexibility.
Standard Configuration
-
Attribute ID: COA_Supplier_IdentificationAttribute1
-
Attribute Name: COA Data Extraction – Supplier Email or Domain
-
- Supplier Location Attributes: Select attributes that contain data for the supplier's location or manufacturing facility.
Standard Configuration
Step 3: Configure Item Identification Attributes by clicking Add Attribute.
Standard Configuration
Step 4: Configure Extraction Attributes by clicking Add Attribute.
When an attribute is added to Extraction Attributes on the AI Extraction Settings page, the 'Extract from COA' toggle is automatically enabled in the Attribute Business Rule Header.
The recommended standard attributes are:
- Manufacturing Date
- Supplier Lot ID
- PO Number
If additional attributes need to be extracted, they can be added here.
AI Prompt (Optional Override)
Each attribute includes an AI Prompt field that applies to all incoming COAs.
- Recommendation: Avoid configuring AI prompts initially. If extraction issues arise, prompts can be customized later for improved accuracy.
Required Attributes
Some attributes include a Required checkbox. By default, key attributes are marked as Required.
- Recommendation: Avoid marking too many attributes as Required, as missing data in COAs may lower processing success rates.