# What is a system prompt and how is it different? — QANATONE > A system prompt is the standing set of instructions an AI app gives the model in the background, setting the assistant role and rules. Kaynak: https://www.qanatone.com/en/nedir/system-prompt-nedir/ --- [Explainers](https://www.qanatone.com/en/nedir/) # What is a system prompt and how is it different? 15 Sep 2026 2 min read Prompting · System Prompt A system prompt is the standing set of instructions an AI app gives the model in the background, setting the assistant role and rules. ## What is a system prompt? In a chat application, the model has already read some text before you type anything. The team behind the app uses that text to define who the assistant is, which topics it covers, which language and tone it uses and what it must not do. This background instruction is the system prompt. Users usually do not see it, but it shapes every answer. ## What goes into a system prompt? Take the support assistant of an online shop. Its system prompt might cover: - Role: it is the shop's support assistant. - Scope: it answers only order, return and shipping questions and politely redirects everything else. - Tone and format: plain language, three sentences at most. - Rules: prices and stock come only from system data, never from guesses. - Handover: angry customers or unsolved problems go to a human. ## How it differs from the user prompt The user's message, the [prompt](https://www.qanatone.com/en/nedir/prompt-nedir/), changes with every conversation. The system prompt stays the same across all of them. Models are trained to give the system prompt priority when the two conflict. That priority is not absolute. Attempts to trick a model into breaking its rules are called prompt injection or jailbreaking, which is why critical rules are also enforced by a separate [guardrail](https://www.qanatone.com/en/nedir/guardrail-nedir/) layer. ## Writing a good system prompt Keep it short and consistent: every rule is sent as [tokens](https://www.qanatone.com/en/nedir/token-nedir/) with every request and takes space in the [context window](https://www.qanatone.com/en/nedir/context-window-nedir/). Giving the reason behind a rule ("never invent a price, because the customer will hold us to it") helps the model handle cases the rule does not spell out. Test every change against real conversations before it goes live. ## More articles [Model Settings · Temperature ### What is temperature in AI models? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/temperature-nedir/)[Core Concept · Token ### What is a token in AI and how is it counted? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/token-nedir/)[Marketing · Turkey ### Digital marketing in Turkey: the market in numbers 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/turkiye-dijital-pazarlama/)[Guide · Free Tools ### Free AI tools: what is available and what are the limits? 15 Sep 2026 · 1 min](https://www.qanatone.com/en/nedir/ucretsiz-yapay-zeka/)[Architecture · Vector Database ### What is a vector database? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/vektor-veritabani-nedir/)[Model Type · VLM ### What is a vision-language model (VLM)? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/vlm-nedir/)[Prompting · Zero-shot ### What is zero-shot prompting? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/zero-shot-nedir/)[Core Concept · LLM ### What are large language models (LLMs) and how do they work? 12 Sep 2026 · 6 min](https://www.qanatone.com/en/nedir/buyuk-dil-modelleri-nedir/)