# System prompt

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: system message, system instructions, developer message, custom instructions, system prompts

Standing [instructions](https://ecosystem.samcarlton.com/prompt) that the builder of an AI product gives the model before any user types. They set the role, rules and tone, and the model gives them priority over the user's messages.

**For example:** A support bot's system prompt says: 'You answer questions about our billing. Keep replies under 100 words. Send refund requests to a human.' Every customer [conversation](https://ecosystem.samcarlton.com/session) starts from those rules.

## Connects to (11)

- [Prompt](https://ecosystem.samcarlton.com/prompt): The instructions or question you give an AI tool in everyday words.
- [Guardrails](https://ecosystem.samcarlton.com/guardrails): Checks and limits built around a model inside a product.
- [AI chat assistant](https://ecosystem.samcarlton.com/chatbot): A finished app where a person types or talks to an AI model and gets replies in conversation.
- [Prompt injection](https://ecosystem.samcarlton.com/prompt-injection): A security weakness in AI products.
- [Harness](https://ecosystem.samcarlton.com/harness): The software wrapped around an AI model that turns it into a working agent.
- [Prefix cache](https://ecosystem.samcarlton.com/prefix-cache): A provider feature that remembers the opening of a request it has just handled.
- [Agent mode](https://ecosystem.samcarlton.com/agent-mode): A named setting in a coding agent that changes how freely it acts.
- [AGENTS.md](https://ecosystem.samcarlton.com/agents-md): A plain text file in a project that many coding agents read automatically at the start of every session.
- [Context engineering](https://ecosystem.samcarlton.com/context-engineering): Deciding what information, instructions, examples and tools to put in front of an AI model for each task, and what to leave out.
- [Prompt optimization](https://ecosystem.samcarlton.com/prompt-optimization): Improving a prompt through repeated testing: change it, run it against a set of examples, measure results and keep the better version.
- [Custom GPTs](https://ecosystem.samcarlton.com/custom-gpts): Versions of ChatGPT that a person sets up for one job, with their own instructions, files and tools, and can share with others.

Map view: https://ecosystem.samcarlton.com/system-prompt
