Day 4 · AI Workflow 90 Part 1 or Bundle Privacy and Sensitive Information

This static page shows the learner task. Runtime access can still be handled by the course shell.

AI Ages Day 4

Part 1 | Week 1 | 15-/30-minute paths

Day 4: Privacy and Sensitive Information

Transform raw workplace material into safe AI input.

15mcore path
30mdeep path
3-5 rows
1export
Current path: 30-minute deep. Complete three rows, one repair note, and export.
1Scenario

Concrete workplace scenario

A customer thread has names, account IDs, order numbers, and internal notes. You want AI to help draft a reply.

It looks like you should paste the thread so AI has enough context. The trap is that the input itself may be unsafe.

2Worked answer before the table

Worked answer

Bad example first: more context can create a privacy problem

Weak example

“Here is the full customer thread with account details and internal notes. Draft a reply.”

What goes wrong

The bad prompt includes the full customer thread, account details, and internal notes with no redaction.

Work-ready version: make the input AI-ready first

Remove

Delete names, IDs, credentials, and confidential notes.

Replace

Use neutral placeholders like [customer], [order], or [policy].

Ask

Escalate if restricted detail is required for the task.

3Decision fork

Quick decision check

The remove / replace / ask rule

Safe AI use starts before the prompt: remove what should not be shared, replace what AI can still reason about, and ask when the boundary is unclear.

Remove

Take out sensitive fields.

Replace

Use safe placeholders.

Ask

Check the approved process if needed.

TRACEToday’s workflow trace

Privacy trace

This is the small visible work change from today. Keep it shallow, real, and reusable tomorrow.

RESULTToday’s visible result

Before / after: what changed in your work?

Use this small contrast to see what changed today. The goal is not more paperwork; it is a clearer AI-in-workflow move.

Before learning

After learning

What AI-in-workflow means today

4Micro-practice

Build today's artifact rows

Complete three short fill-ins. Keep one real work item per row, and change the sample wording so it fits your work.

No.Work itemAI role / prompt caseRisk or evidenceHuman owner / readerNext action
1
2
3
5Repair pass

Repair one weak row

Use this pass to find the row that could confuse someone, create unsafe AI use, or fail as workplace evidence before you export.

Repair example

Weak row: Paste the full customer email thread for AI to rewrite.

Repair move: Remove identifiers and replace private details with placeholders.

Better row: Use [customer], [order], and [issue summary]; omit account ID and internal notes before asking AI for reply structure.

Choose the row you would be comfortable showing to a manager. It should have a clear task, boundary, owner, and next action.

Choose the row most likely to fail, confuse someone, expose sensitive input, or need review.

Write the exact change. Sentence starter: The weak row is weak because ___. I will repair it by adding ___ before using AI.

6Quality gate

Pass / fix / stop standard

Do not paste names, identifiers, credentials, employee records, or confidential terms into AI without an approved process.

7Export artifact

Export artifact

This file is today’s work receipt. It should show what changed in your work habit, not just that you filled a table.

Before you export

  • Did you remove sensitive identifiers?
  • Did you replace needed context with placeholders?
  • Did you avoid pasting restricted notes or credentials?

What this artifact proves: This file proves you can turn raw work input into safe AI-ready input.

Weak export: vague rows, no owner, no repair note, or no next-use line.

Good export: one clear work case, one boundary/rule, one repair note, and one tomorrow-use or manager-use line.

Click Generate Markdown to create privacy_input_filter.md.
Course path

Continue AI Workflow 90

Keep moving through the 90-day workflow portfolio path.