# How to Write a System Prompt That Steers a Model

> System prompt structure: role, rules with reasons, exact output format, tagged examples. Set it in the API system parameter and test it by breaking it.

- Canonical: https://guides-ai.pages.dev/guides/write-a-system-prompt/
- Plate 10.02 · Topic: Prompting (https://guides-ai.pages.dev/topics/prompting/)
- Published: 13 Jun 2026 · Updated: 06 Sept 2026 · 3 min read
- Source site: guides-ai — https://guides-ai.pages.dev/

A [system prompt](/glossary/#system-prompt) is the standing instruction a model reads before every message — its job description. **Four parts cover almost every case: role, rules, format, example.** It goes in the API's `system` parameter, not in the user turn, which is what keeps it from being edited away by the conversation.

## 1. Role, in one sentence

```text
You are a senior technical editor. You turn rough developer notes into clear,
concise documentation for working engineers.
```

Sets identity and audience. Anthropic's guidance is blunt about this: even a single sentence of role changes the tone and focus of everything downstream.

## 2. Rules, with reasons

```text
- Keep sentences short and prefer active voice; this is read on phones.
- Never invent facts. If a detail is missing, write TODO and move on.
- Do not change anything inside code blocks, because they are tested verbatim.
```

Short imperatives, each with the reason attached. That last clause is the upgrade most system prompts are missing — given the motivation, the model generalises to cases you never listed, instead of obeying the letter and missing the point.

## 3. Output format, exactly

```text
Return Markdown: an H2 title, a two-sentence summary, then the edited text.
No preamble, no closing pleasantries.
```

Spells out the shape so you don't post-process. Say what you *do* want; a list of prohibitions leaves the model guessing.

## 4. One tagged example

```text
<example>
Input: the fn returns nil sometimes idk why
Output: ## Bug: function returns nil intermittently
</example>
```

Wrapping examples in tags stops the model reading them as part of the task. Use consistent tag names, and add a second example only if the first leaves an edge case open.

## Test it by breaking it

Write five inputs designed to violate each rule — a note with a code block that begs to be reformatted, one with a missing fact, one twice too long. Run them, find the rule that folded, and tighten only that rule. Repeat. That loop, not length, is what makes a system prompt reliable; formalise it with [LLM-as-judge evals](/guides/llm-as-judge-evals/) once it matters.

The same four parts work in [ChatGPT custom instructions](/guides/chatgpt-custom-instructions/) and in a [CLAUDE.md](/guides/create-claude-md-project-memory/). If the model will read untrusted text, add the defences in [prompt injection defense](/guides/prompt-injection-defense/) — no system prompt survives an injection on its own. Source: [prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices).