Zendesk
Freshdesk
Gorgias
Front
Shopify
Stripe
Slack
Notion
Google Workspace
Confluence
System Prompt
Definition
A system prompt is the underlying set of instructions that defines an AI model's role, behavior, tone, and boundaries for a conversation — set by the developer, not the end user, and applied to every interaction.
How it works
The system prompt is provided to the model before the user's messages and establishes the ground rules: who the agent is, what it should and shouldn't do, how it should sound, and when it should escalate. The model treats it as higher-priority guidance than ordinary user input.
In an AI support platform, the system prompt is where much of the agent's persona, scope, and escalation logic lives — often generated from the plain-English configuration a team sets up.
Why it matters for support
The system prompt is the main lever for keeping an AI agent on-brand, on-policy, and in-scope across every conversation. A well-written one enforces tone, prevents the agent from answering outside its remit, and defines when to hand off to a human.
Frequently asked
What is the difference between a system prompt and a user prompt?
A system prompt is set by the developer to define the agent's role and rules for the whole conversation; a user prompt is the individual message a person sends. The system prompt is treated as authoritative over user input.
Can users see or change the system prompt?
End users normally can't see or change it — that separation is what keeps the agent's behavior consistent and helps defend against prompt injection.
Related terms
Prompt Engineering
Prompt engineering is the practice of designing and refining the instructions given to a language model to get accurate, relevant, and reliable outputs for a specific task..
Prompt Injection
Prompt injection is a security attack where malicious instructions are hidden in user input or external content to manipulate an AI system into ignoring its original instructions or performing unintended actions..
AI Guardrails
AI guardrails are the rules, checks, and constraints placed around an AI system to keep its behavior safe, on-topic, and within policy — controlling what it can say, do, and access..
Plain-English Agent Configuration
In Macha, you configure an agent by writing its rules in plain English in its instructions field — how to triage, what tone to use, what to escalate, what's off-limits — rather than coding logic.
Large Language Model (LLM)
A large language model (LLM) is a neural network trained on vast amounts of text to predict and generate language, enabling it to understand questions, summarize, classify, and write human-like responses..
Put these ideas to work
Macha is an AI agent layer that sits on top of the help desk you already run — Zendesk, Freshdesk, Front, Intercom, or Gorgias.
Start Trial