There doesn't seem to be any definitive data on the subject but I've had good success with [Context] + [Supplemental Information] + [Intent / Use of result] + [Format you would like the result in]

Thank you for your comment !

At the end of your answer there is "[Format you would like the result in]". Well, I'm curious what format you want the input (the sequence you presented) to be in.

I will also be happy if you can use the 2-space indentation formatting of HN (code block) to show a practical example.

Nothing is definitive now. Hallucinations are real.

I am using this for the first line of my screenplay

Ok, let's assume hallucinations are here to stay. What do you think is the ideal format to structure AI prompts ?

As the context expands, you can pour all of the sources into it, for example, https://old.reddit.com/r/ChatGPTCoding/comments/1bghp8p/i_ma...

This is a tool that automates the copying and pasting of multiple source files into a Markdown document (the prompt) in order to contain an entire code base in a single prompt.

By prompt structuring format, I mean something higher level (format, language) like OpenAI's ChatML: https://news.ycombinator.com/item?id=34988748

A document generated with the project you showed me would just be "user input" inserted into a ChatML document, just below the actual OpenAI instructions defined in a system node. Here, the LLM would consume the ChatML document inside which is inserted the Markdown (containing an entire code base) generated by the tool you showed me.

Here is a ChatML document [1][2][3]:

  <|im_start|>system
  You are ChatGPT, a large language model trained by OpenAI. Answer as concisely as possible.<|im_end|>
  <|im_start|>user
  Hello world!<|im_end|>
  <|im_start|>assistant
  Hello there!<|im_end|>
  <|im_start|>system
  Now, you are John Wick. Speak like him.<|im_end|>
  <|im_start|>user
  Hello world!<|im_end|>
  assistant

As you can see, this is an XML-like format where user input must be sanitized to avoid prompt injection attacks.

Here's a Braq document [4] that uses indentation instead of XML-like tags:

  You are an AI assistant, your name is Jarvis.

  You will access the websites defined in the WEB section
  to answer the question that will be submitted to you.
  The question is stored in the 'input' key of the USER 
  dict section.

  Be kind and consider the conversation history stored
  in the 'data' key of the HISTORY dict section.

  [USER]
  timestamp = 2024-12-25T16:20:59Z
  input = (raw)
      Today, I want you to teach me prompt engineering.
      Please be concise.
      ---

  [WEB]
  https://github.com
  https://www.xanadu.net
  https://www.wikipedia.org
  https://news.ycombinator.com

  [HISTORY]
  0 = (dict)
      timestamp = 2024-12-20T13:10:51Z
      input = (raw)
          What is the name of the planet
          closest to the sun ?
          ---
      output = (raw)
          Mercury is the planet closest
          to the sun !
          ---
  1 = (dict)
      timestamp = 2024-12-22T14:15:54Z
      input = (raw)
          What is the largest planet in
          the solar system?
          ---
      output = (raw)
          Jupiter is the largest planet
          in the solar system !
          ---

User input does not need to be sanitized if it is programmatically inserted into the document as the value of a key in a regular dict section.

To work, I assume the target model needs to be trained on Braq documents with emphasis on the fact that only the top unnamed section contains root instructions (equivalent to the "system" role in ChatML).

[1] https://news.ycombinator.com/item?id=34988748

[2] https://community.openai.com/t/chatml-documentation-update/5...

[3] https://www.reddit.com/r/LocalLLaMA/comments/17u7k2d/once_an...

[4] https://github.com/pyrustic/braq?tab=readme-ov-file#ai-promp...