Weigh a decision (pros and cons)

Trade-offs laid out against the stated constraints, with no recommendation — so the analysis informs the decision instead of pre-empting it.

When to use it

Thinking through a genuine trade-off where you want the case laid out cleanly — and specifically do not want the model to decide for you.

What it prevents

The premature recommendation. Asked to weigh options, a model tends to pick one and then marshal the arguments toward it, which is persuasion, not analysis. Forbidding a recommendation and tying every point to the stated constraints keeps it an aid to your judgement rather than a replacement for it.

The prompt

Analyse the two options below and lay out the trade-offs for a decision.

### Output format
A markdown table with four columns: option, the strongest argument for it, the strongest argument against, and who it is the wrong choice for.

### Requirements
- Base every row on the constraints stated in the brief; do not introduce outside assumptions.
- Where the brief is silent on something that would change the answer, list it as an open question below the table.
- Do not recommend a winner; the reader will decide.

### Brief
"""
Build in-house vs buy: a team of three, a six-week deadline, and a feature that is core to the product but not our differentiator.
"""

Why each part is there

Every section of that prompt exists because a specific failure happens without it. These are the checks it passes, and what each one is protecting you from:

• States a concrete task — why this matters
• Avoids vague language — why this matters
• Specifies an output format — why this matters
• Avoids dangling references — why this matters
• Separates data from instructions — why this matters
• Avoids over-aggressive phrasing — why this matters

How to adapt this one

Swap the brief and be explicit about the constraints that actually bind — budget, timeline, team size, what the decision is really about. The analysis is only as good as those inputs. Keep “no recommendation” and “open questions below the table”, which together surface what you would need to know to decide, instead of hiding the uncertainty inside a confident verdict.

The mistake this prompt avoids

Asking “which should I choose?” and getting an answer built on assumptions you never stated. The model fills the gaps in your brief with defaults, then recommends confidently on top of them. Give it the real constraints and ask it to flag what is missing — a recommendation resting on invented premises is worse than no recommendation, because it looks like it did the work.

A variation

Facing more than two options, or a reversible decision? Ask for a shortlist ranked against one explicit criterion you name — reversibility, cost, speed — rather than a full pros-and-cons of each. When the options are many or the stakes are low, a ranked cut against the thing you actually care about is more useful than an exhaustive table you still have to collapse yourself.

Check your version

Once you have adapted it, run it through the checker. The same nine checks that graded this page will grade yours, free and in your browser — paste it in, or build one from scratch by answering a few questions.