Judge the response: volunteer rota

A vague starting prompt is:

Make our volunteer rota.

A plausible before output is:

Assign each volunteer to an available shift and send the schedule.

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 volunteer rota example is being used here to test criteria and verification.

For this page, use the following concrete revision:

Create a draft rota table from these facts: Sam—Tuesday only; Lee—Tuesday or Thursday; Jo—Thursday only; two people needed per shift. Mark gaps instead of assigning unavailable people.

A more useful after output begins:

Tuesday: Sam, Lee. Thursday: Jo, GAP. One additional Thursday volunteer is needed; nobody has been assigned outside stated availability.

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 volunteer rota: 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 volunteer rota: 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 criteria and verification. 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: extra context can be stale, private, or distracting. 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 volunteer rota example is being used here to test criteria and verification.

Suppose the first response invents one detail about volunteer rota. 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 criteria and verification 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 constraint coverage and unsupported assumptions. 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 volunteer rota example is being used here to test criteria and verification.

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 volunteer rota example is being used here to test criteria and verification.

Set a stop rule for this volunteer rota 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.