Appian GenAI Excel Classification Issue with Data vs Empty File

Question

Hi everyone, 
 I&rsquo;m facing an issue while using Appian AI Skill (GenAI) with an Excel file. 
 
 When I upload an Excel file with empty data , I get one type of classification output. 
 However, when I upload the same file structure but with data inside , it produces a different classification output . 
 Essentially, the classification result varies depending on whether the file has data, and it seems inconsistent each time. 
 
 Has anyone experienced this issue before? Any insights on why the classification behavior changes like this?

subhankar-Maantic · Answer

This is expected behavior for GenAI-based classification. 
 Why This Happens: GenAI Classification is Context-Dependent 
 When the file is empty, the model classifies based on: Column headers only File structure and formatting 
 When the file has data, the model classifies based on: Column headers Actual data values Patterns and content within cells 
 These are two different inputs &mdash; different outputs are expected

Shubham Aware · Answer

Classification changes because the model reads the document's actual content, not just the structure. An empty Excel shows only headers, while a populated one adds text and data that shift the classification features; so the same template gets treated as two different documents.

Add both empty and populated files under the same class label in your training set, or convert Excel to PDF before classification (AI Skills work most reliably with PDFs).

Shubham Aware · Answer

Document Classification needs a stable layout (that's why PDFs work). Excel with constantly changing data has no consistent signature, so it lands as Unclassified; more training won't fix it.
Convert each Excel to PDF first, then classify. Or skip the AI model for Excel and route by filename, sender, sheet name, or header row (via Excel Tools plugin) using a rule.