Day 5 · AI Workflow 90 Part 1 or Bundle Human Review Points

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

AI Ages Day 5

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

Day 5: Human Review Points

Place human review before risky steps, not only after an AI answer looks polished.

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

AI drafts a renewal email with discount language, contract terms, and account-risk wording. The draft looks ready to send.

The trap is that different parts need different reviewers. “Looks ready” is not the same as “cleared to send.”

2Worked answer before the table

Worked answer

Bad example first: polished wording hides missing review points

Weak example

“The draft looks good. Send it to the customer.”

What goes wrong

The draft contains discount language, contract terms, and account-risk wording, but has no reviewer named.

Work-ready version: name who checks what and when

What is checked

Discount, terms, risk claim, or customer promise.

Who checks it

Sales, legal, account owner, support lead, or manager.

When it stops

Before send, before approval, before promise, or before escalation.

3Decision fork

Quick decision check

The who-checks-what-when rule

A review point is useful only when it says what is checked, who checks it, and when the work pauses.

What

Which part is risky?

Who

Which owner reviews it?

When

Where does the workflow pause?

TRACEToday’s workflow trace

Review-point 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: AI draft looks good, send renewal email.

Repair move: Name what is reviewed, who reviews it, and when the work pauses.

Better row: Discount line reviewed by sales owner before send; contract wording reviewed by legal before any customer promise.

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 move AI output from draft to action without a named review point for the risky step.

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

  • Does the row say what must be reviewed?
  • Does it name the reviewer?
  • Does it say when the workflow pauses?

What this artifact proves: This file proves you know where an AI draft must pause for human review before action.

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 human_review_point_map.md.
Course path

Continue AI Workflow 90

Keep moving through the 90-day workflow portfolio path.