Introduction

The “Question Refinement Pattern” is focused on improvements on the question itself, to help the LLM to get the “correct” answer. Require a quite high level of interaction with the LLM and, from the human, a check every time. Essentially the idea is asking to the LLM to fine tune the answer itself. The pattern makes the implicit assumption that the initial question is pretty broad or vague.

The Prompt

A way to apply the prompt is the following

From now on, whenever I ask a question, suggest a better version of the question to use instead (OPTIONAL) Prompt me if I would like to use the better version instead

Some LLM tend to use the better version as a default or without confirmation so, sometimes, better clarify which question needs to be picked up.

How to play with the prompt

Crash the prompt in an LLM and start to interact. Put focus on the ‘‘suggested new question’’ as could go off-topic. Start with a broader explicit question, like do I need a car? and see how will converge in the answer.

Some Tests

ChatGPT 5.1

To be honest ChatGPT is not playing ball on this pattern. Being verbose, and immediately switching to a more business-as-usual way to follow up

User: From now on, whenever I ask a question, suggest a better version of the question to use instead. Prompt me if I would like to use the better version instead

Assistant: Got it! I’ll remember to do that going forward. Every time you ask a question, I’ll propose an improved version and then ask if you’d like to use it.

User: do I need a car?

Assistant: Here’s a clearer, more actionable >version of your question: Improved question: “Do I need to own a car for my lifestyle, given where I live, my commute, and my transportation needs?” Would you like to use this improved version instead?

User: yes please

Assistant: Here’s the answer to the improved question: “Do I need to own a car for my lifestyle, given where I live, my commute, and my transportation needs?”

Since I don’t yet know your specific situation, here’s a clear framework to help you decide:

  • Your commute is long or not served by transit.
  • You regularly do errands requiring carrying items.
  • You travel to rural/suburban >areas often.
  • Your schedule varies, making transit inconvenient.
  • You might not need a car if:
  • You live in a walkable city with reliable transit.
  • Your commute is short. - Rideshare costs are lower than car ownership costs.
  • You work remotely.
  • You can use car‑sharing services for occasional trips.

Financial test: A car is worth it if the benefit you gain exceeds the true cost (often $500–$1,000/month in the U.S.). I can give a precise recommendation if you tell me: - Your city/region - Your commute distance and frequency - Your transit options Would you like to provide those details?

Claude - Haiku

CLaude Haiku plays ball decently. It suggests a diffent version, clarify the reason behind and ask if we want to use the new one.

Haiku Prompt

Llama 3.2

LLama 3.2 on Ollama is pretty “short” in the answer and also adding an interesting disclaimer

Llama Prompt

Qwen 3

Qwen 3 on Ollama plays ball in a a more interesting way. It accept the prompt, suggests some alternate questions and iterate on it.

Qwen 3 Prompt

Mistral

mistral instead is pretty verbose in the suggestion of questions, creating a bit of a “wall of words” for the end users

Mistral Prompt

Conclusion

The prompt is mostly usefult to refine and clarify the intentions of the user. The answer is quite variable according to the various LLM creating, in a couple of cases, some digression.