
Should This Be AI?
The wrong-tool test. Find out which steps of your work need AI, and which need a simple program, a checklist or a person.
How it works
- Name the steps of one workflow.
- Answer a few short questions about each step.
- See which tool fits each step, and the rule that decided it.
Load an example workflow
Each example replaces your steps with four answered ones.
Your workflow
Up to 8 steps. Names stay in this browser tab and are not stored.
Step 1
Worth a conversation
Answer the not-sure questions to sharpen this
We need to know what a mistake here would cost before we can suggest a tool. Answer question 3.
Your answers that decided it
- Costly mistake
- Not answered
Rule R1, rubric 2.0.0
rules/R1.ts
import type { Rule } from '../rubric' export const R1: Rule = { id: 'R1', reads: ['costly'], when: (a) => a.costly !== 'yes' && a.costly !== 'no', verdict: 'unclear', humanSignOff: () => false, why: 'We need to know what a mistake here would cost before we can suggest a tool. Answer question 3.', }
Your workflow at a glance
This is also what "Send us this result" sends.
| Step | Verdict | Reason | Rule |
|---|---|---|---|
| Step 1 | Worth a conversation | We need to know what a mistake here would cost before we can suggest a tool. Answer question 3. | R1 |
Send us this result
Opens our contact page with these results in the message. You can edit them before sending.
Results from Should This Be AI? (the wrong-tool test) Step 1: not answered yet (rule R1, rubric 2.0.0) What I would like help with:
How the verdicts are made
Every verdict comes from a fixed set of rules written in code. For any set of answers exactly one rule matches, so the same answers always give the same verdict. Nothing you type leaves this page unless you send it to us, or run a live test, which sends that test's text to Amazon Bedrock.
Rubric version 2.0.0