System Prompt

  • Last Updated 23 April, 2026
  • 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.

System Prompt: Book Excerpts and Blog Articles

Free online book excerpts with full text chapters online and free PDF downloads, and the Aussie AI blog, including related articles:

Research on System Prompts

Research papers include:

More AI Research

Read more about: