Steelman the counterargument to your position
The strongest case a smart critic would actually make against you, plus the single crux that would settle which side is right.
Last updated
Fill in the blanks
Assembled in your browser — nothing you type is stored or sent anywhere.
Your prompt
Model-agnostic — works in Claude, ChatGPT, Gemini or any AI chat.
Why this prompt works
- →Explicitly demanding the strongest version, not an easy one, directly fixes the tendency to generate a counterargument that flatters the stated position.
- →Asking for a single crux instead of a list of objections forces the answer toward what would actually change your mind, rather than a diffuse pile of disagreements.
- →Permission to say "my reasoning already covers this" stops the model from padding the response with a manufactured objection just to look balanced.
Part by part
- the STRONGEST version of the opposing case
- Steelmanning rather than balance. A model asked for counterarguments will produce a list including weak ones, which is reassuring and useless.
- a smart, well-informed critic who disagrees with me
- Names the imagined author. It shifts the output from generic objections to the argument someone would actually make.
- not a weak version that's easy to dismiss
- Explicitly rules out the strawman, which is the default failure — and the one that makes the exercise feel productive while changing nothing.
- the one fact, definition or value disagreement
- Three categories of crux, which is what makes the request answerable. Most disagreements are one of the three, and naming which one is most of the work.
- say that plainly instead of manufacturing a new objection
- Permission to conclude that your reasoning holds. Without it, a model invents an objection to appear even-handed.
Common mistakes
What are the counterarguments to this position?Returns a list of objections of mixed quality, including several that are easy to answer. Working through weak objections builds confidence without testing anything.
Argue against my position.Produces adversarial argument rather than the best case, so it reaches for rhetorical moves. Steelmanning asks for the version a thoughtful person believes, which is a different and more useful thing.
Give me a balanced view of both sides.Balance implies the two sides deserve equal weight, which is often false. Steelmanning does not require pretending the strongest opposing case is as strong as yours.
Questions
What is a crux exactly?
The thing that, if it turned out differently, would change your mind. Naming it converts an argument into a question — sometimes an empirical one you can go and answer, which is the most useful outcome available.
Why does the strawman version feel so satisfying?
Because dismissing a weak objection produces the feeling of having tested a belief. That is exactly why it is worth asking for the strongest version explicitly — the reassuring output is the one to avoid.
What if my position is genuinely well supported?
The prompt says to state that. Manufacturing an objection to appear balanced is a real failure mode, and a model told it may conclude your reasoning holds gives a much more informative answer.
Is this useful before writing rather than after?
Especially then. Knowing the strongest objection before drafting means addressing it in the argument rather than bolting on a rebuttal, which reads defensive and arrives too late to change the structure.