AI Extraction Skill Returning Concatenated Text with Unexpected Numbers in Appian 26.9

Hi Appian Community,

I am working on an AI-powered document extraction process in Appian 26.9. I have created an AI Skill to extract information from different types of insurance-related documents, such as:

• Police Reports

• Driving Licences

• Vehicle Registration Certificates (RC)

• Repair Invoices

The AI Skill is successfully extracting the required information, but I am facing an issue with the output format.

1. Issue with the extracted output

Instead of returning properly structured data, the AI Skill is returning all the extracted field names and their corresponding values as a single concatenated text string.

For example, for a Driving Licence document, I am getting the following output:

LicenseNumberVehicleTypeVehicleRegistrationNumberRcNumberDateNameDL-TRN-RJ-0002-263Scooter3RJ-27-TR-90023RC-TRN-RJ-0002-26314 October 20263Aisha Khan3

As you can see, the field names and values are joined together without any separators or proper formatting.

2. Unexpected number '3' in the output

I have also noticed that the number 3 is appearing at multiple places in the extracted data, even though it is not expected as part of the actual field values.

I am not sure why this number is being appended to the extracted information.

My questions:

1. Why is the AI Skill returning all field names and values as a single concatenated text string instead of properly structured output?

2. Why is the number 3 appearing between or at the end of extracted values?

3. Is this related to the AI Skill's output configuration, prompt instructions, or the way Appian 26.9 processes extraction results?

4. What is the recommended way to get structured extraction output (for example, JSON or individual field-value pairs) so that I can easily map the extracted values to Appian process variables?

I would appreciate any suggestions or guidance on how to resolve this issue.

Appian Version: 26.9

Thank you!