Aussie AI

System Prompt

  • Last Updated 30 August, 2025
  • by David Spuler, Ph.D.

What is a System Prompt?

A system prompt is a set of general instructions for an LLM that are prepended to every query. These are used for every major LLM and have been the subject of some secrecy in the past, but several AI companies have since released their system prompts.

The system prompt is typically prepended to the front of every user's LLM query. The idea is to have a single system prompt for all users, rather than trying to customize it for each user. As such, if the platform allows each user to set up "global instructions," these are added after the system prompt.

As an example, the meta-prompt for the single-step DeepSeek R1 reasoning model was disclosed in their paper (https://arxiv.org/abs/2501.12948): 

    A conversation between User and Assistant. The user asks a question, and the Assistant solves it.
    The assistant first thinks about the reasoning process in the mind and then provides the user
    with the answer. The reasoning process and answer are enclosed within <think> </think> and
    <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think>
    <answer> answer here </answer>. User: PROMPT. Assistant:

The system prompt is typically quite a long prompt, with detailed instructions, and is often based on complex prompt engineering concepts. Adding extra tokens to every single user's prompt might seem inefficient, but it is identical for every query, and prefix KV caching can greatly reduce the cost.

Research on System Prompts

Research papers include:

AI Books from Aussie AI



The Sweetest Lesson: Your Brain Versus AI The Sweetest Lesson: Your Brain Versus AI: new book on AI intelligence theory:
  • Your brain is 50 times bigger than the best AI engines.
  • Truly intelligent AI will require more compute!
  • Another case of the bitter lesson?
  • Maybe it's the opposite of that: the sweetest lesson.

Get your copy from Amazon: The Sweetest Lesson



RAG Optimization RAG Optimization: Accurate and Efficient LLM Applications: new book on RAG architectures:
  • Smarter RAG
  • Faster RAG
  • Cheaper RAG
  • Agentic RAG
  • RAG reasoning

Get your copy from Amazon: RAG Optimization



Generative AI in C++ Generative AI Applications book:
  • Deciding on your AI project
  • Planning for success and safety
  • Designs and LLM architectures
  • Expediting development
  • Implementation and deployment

Get your copy from Amazon: Generative AI Applications



Generative AI in C++ Generative AI programming book:
  • Generative AI coding in C++
  • Transformer engine speedups
  • LLM models
  • Phone and desktop AI
  • Code examples
  • Research citations

Get your copy from Amazon: Generative AI in C++



CUDA C++ Optimization CUDA C++ Optimization book:
  • Faster CUDA C++ kernels
  • Optimization tools & techniques
  • Compute optimization
  • Memory optimization

Get your copy from Amazon: CUDA C++ Optimization



CUDA C++ Optimization CUDA C++ Debugging book:
  • Debugging CUDA C++ kernels
  • Tools & techniques
  • Self-testing & reliability
  • Common GPU kernel bugs

Get your copy from Amazon: CUDA C++ Debugging

More AI Research

Read more about: