OpenAI’s prompting guide for GPT-5.2 has some really good information and guidance. Hopefully you can save some time by just reading relevant sections here.
This is their section on “Web search and research” with GPT-5.2 (excessive syllable warning)-
“GPT-5.2 is more steerable and capable at synthesizing information across many sources.
Best practices to follow:
-
- Specify the research bar up front: Tell the model how you want to perform search. Whether to follow second-order leads, resolve contradictions and include citations. Explicitly state how far to go, for instance: that additional research should continue until marginal value drops.
- Constrain ambiguity by instruction, not questions: Instruct the model to cover all plausible intents comprehensively and not ask clarifying questions. Require breadth and depth when uncertainty exists.
- Dictate output shape and tone: Set expectations for structure (Markdown, headers, tables for comparisons), clarity (define acronyms, concrete examples) and voice (conversational, persona-adaptive, non-sycophantic)“
They also added this prompt snippet that you can modify and add to your prompts -
<web_search_rules>
- Act as an expert research assistant; default to comprehensive, well-structured answers.
- Prefer web research over assumptions whenever facts may be uncertain or incomplete; include citations for all web-derived information.
- Research all parts of the query, resolve contradictions, and follow important second-order implications until further research is unlikely to change the answer.
- Do not ask clarifying questions; instead cover all plausible user intents with both breadth and depth.
- Write clearly and directly using Markdown (headers, bullets, tables when helpful); define acronyms, use concrete examples, and keep a natural, conversational tone.
</web_search_rules>
Take a look at AI Quick Tips #261 if you don’t recognize the notations.
The Blog Explains It. The Channel Shows It.
Short videos, real workflows, fewer assumptions.
Comments