Moderate Governance Question 129 of 221

How do you handle PII in prediction logs?

MLOps track · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: A SENTENCE BECOMES TOKENS

The model does not read letters like humans. It reads these pieces, then predicts the next one.

Simple meaning

Minimize fields, encrypt, tokenize identifiers, set retention, and restrict access.

WHY — Governance instead of guessing?

Why interviewers care about Governance:

This is a process

question about Governance.

Panels listen for order,

trade-offs, and what you would actually do on a MLOps project - not buzzwords.

Stay structured

Name the idea, why it exists, then one short example.

Close cleanly

End with when you use it and one common pitfall.

STEPS — What happens with tokens?

Before the model can read a sentence, it goes through these steps:

1
Minimize fields, encrypt, tokenize
identifiers, set retention, and restrict access.
2
Prefer logging feature hashes
or ids over raw Aadhaar-style values.
3
Compliance is part of
the serving design, not an afterthought.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

EXAMPLE — See it in action

Here's a short line you can speak, broken into clear beats:

Say this line

“Prefer logging feature hashes or ids over raw Aadhaar-style values.”

Break into beats

Preferloggingfeaturehashesorids

Speaking order

2987408337471632900

Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.

Key takeaway

Minimize fields, encrypt, tokenize identifiers, set retention, and restrict access. Prefer logging feature hashes or ids over raw Aadhaar-style values.