AI Codex
Tools & EcosystemOperatorsDevelopers

System Prompt

Also: system instruction, system message

A system prompt is the set of instructions you give Claude before the conversation starts — telling it who it is, what it's for, what it should and shouldn't do, and how to behave. Users see the conversation; they typically don't see the system prompt. It's the configuration layer between you as an operator and Claude as a product. Writing a good system prompt is one of the highest-leverage things you can do when deploying Claude.

In practice

You're building a customer service bot for a software company. You write a system prompt that says: "You are a helpful support agent for Acme Inc. Only answer questions about our product. Never discuss competitors. If a customer wants a refund, direct them to billing@acme.com." Claude reads this before every conversation and behaves accordingly — your users never see it.

Related concepts

Where System Prompt shows up

10 articles

The system prompt is the most powerful thing you control in Claude. Most people write them once, poorly, and wonder why outputs are inconsistent. Here's the method.

Implementation guide·How to write a system prompt that actually works·7 min

Most "prompt engineering" advice is either too academic or too simplistic. Here is the practical version — the five things that reliably improve outputs.

Implementation guide·Prompt engineering for operators: what actually matters·6 min

The most common reason AI-assisted work falls apart after delivery: the client can't maintain what you built. Here's how to hand off Claude-powered workflows so they actually stick.

Implementation guide·Client handoff: giving Claude the context it needs to work on your accounts·6 min

Most prompt problems aren't caused by bad AI — they're caused by the same three things: no role, no context, no constraint. Here's how to fix all three in under two minutes.

Implementation guide·How to write a good prompt·6 min

The .claude folder has five layers. Most teams set up one and wonder why they keep correcting Claude. Here is what to configure in what order — and what you can skip entirely.

Implementation guide·Setting up Claude Code for your team: the leverage-ordered guide·9 min

The system prompt is the highest-leverage thing you control when deploying Claude. Most are either too vague or too long. Here's what good looks like.

Role-Specific·Writing a system prompt that actually works·6 min

The most common reason professionals hold back from using Claude for real work: they're not sure whether they're putting confidential information at risk. Here's the direct answer.

Role-Specific·What's safe to share with Claude — and what isn't·6 min

The system prompt is where you stop asking Claude to be general-purpose and start making it yours. Most operators underuse it.

Core Definition·How to brief Claude before the conversation starts·4 min

More instructions don't mean better results. Most system prompts fail in one of five predictable ways — and fixing them is usually the highest-leverage thing you can do to improve your Claude integration.

Failure Modes·The system prompt mistakes that make Claude worse, not better·5 min

The security vulnerabilities in most Claude apps aren't exotic — they're the same three mistakes: leaking system prompts, ignoring prompt injection, and trusting user input in tool calls. Here's how to fix all three.

Failure Modes·Security issues in Claude-powered apps (and how to avoid them)·8 min