Complete a realistic workflow: maintenance questions

A vague starting prompt is:

What should I ask the repairer?

A plausible before output is:

Ask about the cause, cost, parts, timeline, warranty, and whether the repair is worth doing.

The text sounds agreeable but cannot yet support a decision. It hides assumptions, supplies no inspection point, and does not show whether the result fits the real situation. Diagnose those defects before adding instructions. Prompt improvement is not decoration; each added phrase should control a known source of variation. This maintenance questions example is being used here to test before-and-after execution.

For this page, use the following concrete revision:

Create six questions for a technician about a washing machine that stops mid-cycle. Facts: error E03, filter cleaned, appliance unplugged now. Do not diagnose or advise opening it.

A more useful after output begins:

1. What does E03 mean for this model? 2. What tests will you perform? 3. What is the call-out cost before parts? 4. Should it remain unplugged until inspection?

The after output is easier to inspect because it follows explicit constraints and makes at least one uncertainty visible. Compare it with the before output line by line for maintenance questions: identify what came from source facts, what the model generated, and which decision still belongs to a person. Before acting, verify the claim with the highest consequence.

Judge the response against three criteria specific to maintenance questions: does it honor the requested form, does it rely only on supplied facts, and can the intended person act on it? Add a fourth criterion for before-and-after execution. If a criterion matters, state a pass condition before asking for another draft so the model does not move the goalposts for you.

Remember the main limit: home details can expose sensitive routines or create unsafe advice. A conversational response predicts suitable language from context; it does not inspect your home, understand institutional rules, call an expert, or accept responsibility. When the missing fact concerns safety, rights, health, money, assessment rules, or a relationship, turn the output into questions for an appropriate source. This maintenance questions example is being used here to test before-and-after execution.

Suppose the first response invents one detail about maintenance questions. Quote the unsupported phrase and ask: “Keep the current format, remove that phrase, mark the missing fact as a question, and change nothing else.” This controlled follow-up tests before-and-after execution while preserving material that already meets the quality bar.

Then ask the model to identify which statements came from your context and which it generated. Treat that labelling as an aid, not proof. Verify the highest-consequence statement using practical fit, privacy, and human approval. For the course case, write the source beside the checked statement and name who gives final approval. This creates a small audit trail that survives after the chat scrolls away. This maintenance questions example is being used here to test before-and-after execution.

Minimise context before maximising it. Replace names with roles, remove addresses and account identifiers, summarise sensitive messages, and avoid uploading material you are not entitled to share. If the task can be completed with a blank template or offline checklist, that may be the better method. Relevance, not volume, is the standard. This maintenance questions example is being used here to test before-and-after execution.

Set a stop rule for this maintenance questions exercise: stop after two targeted revisions if the response still invents constraints, ignores the format, or requires facts the tool cannot verify. At that point, complete the artifact yourself or consult a person. Knowing when conversation is no longer useful is part of proficient AI use.