Day 2 · AI Workflow 90 Part 1 or Bundle Task Fit Before Prompting

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

AI Ages Day 2

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

Day 2: Task Fit Before Prompting

Check whether a task is safe, useful, and ready before writing a prompt.

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 manager says: “Can you use AI to handle this customer escalation and tell me what we should do?”

It sounds like a prompt-writing task. The trap is that the work is not ready for AI until you know the owner, usable input, risk, and stop condition.

2Worked answer before the table

Worked answer

Bad example first: the request sounds useful, but the task is not fit yet

Weak example

“Read this escalation and decide the best response for the customer.”

What goes wrong

The prompt asks AI to decide the best response with no owner named, unknown evidence, and no stop condition.

Work-ready version: check fit before prompting

Fit to draft

AI can draft a neutral summary if the input is safe and approved.

Fit to prepare

AI can list missing facts, options, and questions for the owner.

Not fit to decide

AI must not own the escalation outcome or customer-impact decision.

3Decision fork

Quick decision check

The fit-before-prompt rule

Before you prompt, check four things: owner, input, risk, and stop. If one is missing, repair the task before asking AI to produce output.

Owner

Who owns the outcome?

Input

What can AI safely use?

Risk

What could go wrong?

Stop

Where must AI stop?

TRACEToday’s workflow trace

Task-fit 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: Ask AI to handle customer escalation.

Repair move: Add owner, safe input, risk, and stop condition.

Better row: AI may summarize escalation notes; support lead owns the customer decision; AI stops before refund or policy 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 prompt AI to complete a task before owner, input, risk, and stop condition are clear.

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 each row name the owner?
  • Does it say what input AI can safely use?
  • Does it define where AI must stop?

What this artifact proves: This file proves you checked owner, input, risk, and stop condition before prompting AI.

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 task_fit_decision_note.md.
Course path

Continue AI Workflow 90

Keep moving through the 90-day workflow portfolio path.