Prompt element of the day · Follow or Bounce

Keywords (Kw)

2026-10-28T00:00:00-07:00

Words or names that must appear, or that pin down the topic.

Keywords mark the subject terms the answer must be about. They work as a relevance test: an answer that never touches them has drifted off the question.

Watch out: A long keyword list turns into word salad. Pick the few terms that truly matter, and check they are used correctly, not just dropped in.

Statistics (St)

2026-10-27T00:00:00-07:00

Numbers that support a claim, such as counts, averages or rates.

Using a number to support a general claim is a form of induction. A number supports a claim only if it is real, recent and about the right group.

Watch out: Models can produce precise-looking numbers with no real source. Supply your own data where possible, and trace every number to its origin before you repeat it.

Call to action (Ca)

2026-10-26T00:00:00-07:00

The next step the answer should end on, for you or for the people who read it.

An argument can end in a practical conclusion: a decision about what to do. A call to action turns the reasoning into one clear next step.

Watch out: Pushy calls to action backfire. Ask for one clear, honest next step, not pressure or invented urgency like 'only two places left'.

Call to action (Ca)

2026-10-25T00:00:00-07:00

The next step the answer should end on, for you or for the people who read it.

An argument can end in a practical conclusion: a decision about what to do. A call to action turns the reasoning into one clear next step.

Watch out: Pushy calls to action backfire. Ask for one clear, honest next step, not pressure or invented urgency like 'only two places left'.

Format (Fm)

2026-10-24T00:00:00-07:00

The shape of the answer: a list, a table, steps, an email or a short paragraph.

Format is a constraint on form, not content. It answers Grice's advice to be orderly: the same information is easier to check in a shape you can scan.

Watch out: A neat table can make guesses look like facts. Format makes an answer easier to read, not more reliable.

Citations (Ci)

2026-10-23T00:00:00-07:00

Sources the answer should point to, so you can check where each claim comes from.

A citation links a claim to its evidence. It serves Grice's maxim of Quality: do not say things you lack adequate evidence for.

Watch out: Models can invent citations that look real: plausible titles, authors and links that do not exist. Give your own sources when you can, and open every citation before trusting it.

Objective (Ob)

2026-10-22T00:00:00-07:00

What you want the answer to achieve: the point of the whole request.

The objective is the conclusion you are reasoning toward. Without it, relevance has no anchor, since Grice tied relevance to the purpose of the conversation.

Watch out: Stating a goal can tilt the answer toward it. Ask 'help me decide' rather than 'convince me', unless you really want only one side.

Examples (Ex)

2026-10-21T00:00:00-07:00

One or more samples of what a good answer looks like.

Examples work by induction: from a few cases the model infers a general pattern. Like any induction, the pattern it picks may not be the one you meant.

Watch out: Models can copy examples closely, including their accidents. If all your examples are food words, expect more food words. Vary them on purpose.

Objective (Ob)

2026-10-20T00:00:00-07:00

What you want the answer to achieve: the point of the whole request.

The objective is the conclusion you are reasoning toward. Without it, relevance has no anchor, since Grice tied relevance to the purpose of the conversation.

Watch out: Stating a goal can tilt the answer toward it. Ask 'help me decide' rather than 'convince me', unless you really want only one side.

Audience (Au)

2026-10-19T00:00:00-07:00

Who will read or use the answer, and what they already know.

Sets the shared background the answer can assume. What counts as informative enough depends on the listener, so the audience fixes how much to explain.

Watch out: A vague audience like 'beginners' helps less than saying what they already know and what they need to do with the answer.

Quotes (Qu)

2026-10-18T00:00:00-07:00

Exact words from a real person or text, repeated word for word.

A quotation is testimony: evidence that someone said something. It counts only if it is accurate and in context. A misquote is a false premise.

Watch out: Models can invent quotations or pin real ones on the wrong person. Paste the exact words yourself, or check any quote against a reliable original.

Language (La)

2026-10-17T00:00:00-07:00

Which language to answer in, and how plain or technical the wording should be.

A statement only works if both sides read it the same way. Choosing the language and reading level avoids obscurity, which Grice's maxim of Manner warns against.

Watch out: A translation can sound fluent and still be wrong. For anything important, like medicine labels or contracts, ask a fluent speaker to check it.

Limitations (Li)

2026-10-16T00:00:00-07:00

Rules the answer must obey, such as length, cost or things to avoid.

Limitations are necessary conditions: an answer that breaks one fails, however good it is otherwise. Meeting every limitation still does not make an answer good enough.

Watch out: Check the answer against each limit yourself. Models sometimes quietly break a rule, such as a word count, while sounding as if they kept it.

Call to action (Ca)

2026-10-15T00:00:00-07:00

The next step the answer should end on, for you or for the people who read it.

An argument can end in a practical conclusion: a decision about what to do. A call to action turns the reasoning into one clear next step.

Watch out: Pushy calls to action backfire. Ask for one clear, honest next step, not pressure or invented urgency like 'only two places left'.

Deadline (Dl)

2026-10-14T00:00:00-07:00

The time frame your task, or the information you need, belongs to.

Mostly practical, not logical. A chat model answers when asked, not on a schedule. The logical part is a time index: many claims are true only as of a date.

Watch out: Models have a knowledge cutoff and may not know today's date. For anything time-sensitive, give the date yourself and check recent facts elsewhere.

Quotes (Qu)

2026-10-13T00:00:00-07:00

Exact words from a real person or text, repeated word for word.

A quotation is testimony: evidence that someone said something. It counts only if it is accurate and in context. A misquote is a false premise.

Watch out: Models can invent quotations or pin real ones on the wrong person. Paste the exact words yourself, or check any quote against a reliable original.

Statistics (St)

2026-10-12T00:00:00-07:00

Numbers that support a claim, such as counts, averages or rates.

Using a number to support a general claim is a form of induction. A number supports a claim only if it is real, recent and about the right group.

Watch out: Models can produce precise-looking numbers with no real source. Supply your own data where possible, and trace every number to its origin before you repeat it.

Deadline (Dl)

2026-10-11T00:00:00-07:00

The time frame your task, or the information you need, belongs to.

Mostly practical, not logical. A chat model answers when asked, not on a schedule. The logical part is a time index: many claims are true only as of a date.

Watch out: Models have a knowledge cutoff and may not know today's date. For anything time-sensitive, give the date yourself and check recent facts elsewhere.

Tone (To)

2026-10-10T00:00:00-07:00

The emotional colour of the reply: friendly, formal, firm, playful or calm.

Tone changes how something is said, not what is claimed. Logic separates content from expression, and tone is a request about expression.

Watch out: Tone can blur content. If you ask for 'reassuring', check the reply has not softened a fact you needed to hear plainly.

Objective (Ob)

2026-10-09T00:00:00-07:00

What you want the answer to achieve: the point of the whole request.

The objective is the conclusion you are reasoning toward. Without it, relevance has no anchor, since Grice tied relevance to the purpose of the conversation.

Watch out: Stating a goal can tilt the answer toward it. Ask 'help me decide' rather than 'convince me', unless you really want only one side.

Statistics (St)

2026-10-08T00:00:00-07:00

Numbers that support a claim, such as counts, averages or rates.

Using a number to support a general claim is a form of induction. A number supports a claim only if it is real, recent and about the right group.

Watch out: Models can produce precise-looking numbers with no real source. Supply your own data where possible, and trace every number to its origin before you repeat it.

Context (Cx)

2026-10-07T00:00:00-07:00

The background facts of your situation that the answer should build on.

Context supplies the premises: the statements taken as given. A conclusion is only as good as the premises it starts from.

Watch out: False premises give confident nonsense. If your background facts are wrong or out of date, a well-reasoned answer is likely to be wrong too.

Keywords (Kw)

2026-10-06T00:00:00-07:00

Words or names that must appear, or that pin down the topic.

Keywords mark the subject terms the answer must be about. They work as a relevance test: an answer that never touches them has drifted off the question.

Watch out: A long keyword list turns into word salad. Pick the few terms that truly matter, and check they are used correctly, not just dropped in.

Call to action (Ca)

2026-10-05T00:00:00-07:00

The next step the answer should end on, for you or for the people who read it.

An argument can end in a practical conclusion: a decision about what to do. A call to action turns the reasoning into one clear next step.

Watch out: Pushy calls to action backfire. Ask for one clear, honest next step, not pressure or invented urgency like 'only two places left'.

Citations (Ci)

2026-10-04T00:00:00-07:00

Sources the answer should point to, so you can check where each claim comes from.

A citation links a claim to its evidence. It serves Grice's maxim of Quality: do not say things you lack adequate evidence for.

Watch out: Models can invent citations that look real: plausible titles, authors and links that do not exist. Give your own sources when you can, and open every citation before trusting it.

Audience (Au)

2026-10-03T00:00:00-07:00

Who will read or use the answer, and what they already know.

Sets the shared background the answer can assume. What counts as informative enough depends on the listener, so the audience fixes how much to explain.

Watch out: A vague audience like 'beginners' helps less than saying what they already know and what they need to do with the answer.

Questions (Qs)

2026-10-02T00:00:00-07:00

An invitation for the model to ask you what it needs before it answers.

Questions turn a one-shot guess into a dialogue. Missing premises get supplied instead of assumed, so the answer can be as informative as you need.

Watch out: The model's questions are only as useful as your answers. Answer honestly and specifically; if you guess, it will build on your guess.

Limitations (Li)

2026-10-01T00:00:00-07:00

Rules the answer must obey, such as length, cost or things to avoid.

Limitations are necessary conditions: an answer that breaks one fails, however good it is otherwise. Meeting every limitation still does not make an answer good enough.

Watch out: Check the answer against each limit yourself. Models sometimes quietly break a rule, such as a word count, while sounding as if they kept it.

Analogies (An)

2026-09-30T00:00:00-07:00

A comparison with something familiar that helps explain something new.

An analogy maps the structure of a known case onto a new one. It explains and can suggest, but it never proves; test it by finding where it breaks.

Watch out: Every analogy breaks somewhere. Ask the model to say where its comparison stops working, so you do not carry the wrong part over.

Context (Cx)

2026-09-29T00:00:00-07:00

The background facts of your situation that the answer should build on.

Context supplies the premises: the statements taken as given. A conclusion is only as good as the premises it starts from.

Watch out: False premises give confident nonsense. If your background facts are wrong or out of date, a well-reasoned answer is likely to be wrong too.