I really appreciate that Instructure is posting "Nutrition Facts" for all of its AI-connected tools. I am wondering, however, about this statement in all of them: 
When we asked ChatGPT what this means, the response is:
-
Canvas does not intentionally send structured PII fields (like names, emails, or IDs from the Canvas user profile) to the AI model.
-
However, if a user types PII into the discussion reply itself, that text content may be sent to the model, because it’s part of the reply being summarized.
-
For example, if a student writes: “Hi, I’m Jordan Smith, and my ID number is 1234567…”, that whole message is part of the source text, and thus may be passed to the LLM for summarization.
-
“PII is not exposed” likely refers to not displaying that PII in the final generated summary, but not necessarily excluding it from the model’s processing pipeline.
Summary
|
Statement
|
Meaning
|
|
"PII is not exposed"
|
Likely means PII is not shown in the final summary output
|
|
"PII in discussion replies may be sent"
|
If students include PII in their own messages, that full content could be sent to the LLM
|
|
"No PII is intentionally sent"
|
Canvas isn’t explicitly sending PII fields from Canvas accounts to the model
|
I'm wondering if someone at Instructure could clarify. I think this is an important consideration in decisions regarding the use of these tools.
Thank you,
Lisa Beach