You give ChatGPT an instruction, it follows it properly for three messages, then drifts right back to its usual style. That's not a flaw in the tool: you wrote a one-off instruction, not a system prompt. A system prompt is the frame you set before the conversation starts: a role, some context, rules, an output format. The model keeps it in view at every exchange, which makes it far more stable than a sentence tossed in halfway through.
Here you'll see exactly what a system prompt contains, the five blocks that make it solid, a complete example you can adapt in ten minutes, and three places to install it depending on the tool you use. You'll also see why rules sometimes start slipping in long conversations, and the simple habits that fix most cases. No technical skills required: it all happens in plain language, in a standard interface.
What a system prompt actually is
A system prompt is a set of instructions placed above the conversation: it defines who the AI should be, what it should know, and what it has to respect — and it stays active for every single message you send.
The closest analogy is a job description. The system prompt is the job description: role, scope, internal rules, format of the deliverables. Your message today is the one-off request: ‘write up the quote for Ms. Lefèvre'. A new hire you repeat the job description to before every single request would find you very strange. An AI, on the other hand, needs exactly that — and that's precisely what the system prompt does: it re-reads it every turn without you having to retype a thing.
The name changes from tool to tool, but the mechanism is identical everywhere:
- in ChatGPT, they're called custom instructions (and project instructions);
- in Claude, project instructions;
- in Gemini, Gems;
- on the developer side, a parameter called system sent with every request.
The concrete difference from a normal message: your message stays one item in a history of dozens, whereas the system prompt is treated as a priority framing instruction. That's why a rule written in the right place holds up ten times better than the same rule sent in your third message.
The five blocks of a system prompt that goes the distance
A reliable system prompt always contains the same five blocks: role, context, rules, format, and guardrails. If one is missing, that's almost always where the AI goes off the rails.
| Block | The question it answers | Short example |
|---|---|---|
| Role | Who's talking? | You are a copy editor for an accounting firm. |
| Context | For whom, in what setting? | Our readers run small businesses and have no accounting background. |
| Rules | What to do, what to avoid? | Sentences of 20 words max, no jargon. |
| Format | What does a good answer look like? | One heading, three paragraphs, a three-item list. |
| Guardrails | What to do when in doubt? | If a piece of data is missing, ask instead of making it up. |
Here's a complete example, deliberately ordinary and very specific, for a small business:
Role: you are a writing assistant for Atelier Vermeil, a small custom joinery shop in Nantes with two employees.
Context: our customers are homeowners having a staircase or a built-in bookcase made to measure. Project budgets run from 4,000 to 12,000 euros. They usually compare three quotes before choosing.
Rules: write in French, using the formal vous with the customer. Sentences of 20 words max. Never give a specific lead time (I approve those myself). Never use the phrase ‘cheap'. Mention solid wood whenever the subject allows.
Format: one heading, three 60-word paragraphs, a three-item list, a one-line call to action.
Check: if information is missing (dimensions, wood species, access constraints), ask me instead of inventing it. At the end of the message, flag any rule you couldn't follow.
That prompt is under 150 words, and yet it eliminates most of the corrections you'd otherwise make by hand. Three details do the work: the rules are countable and checkable (‘20 words max' is measurable, ‘be concise' isn't), the things to avoid are named explicitly, and the last block gives the AI permission to ask a question rather than paper over a gap. To go deeper on how to phrase the instructions themselves, the complete method for writing a good prompt breaks down each building block.
When the rules start slipping
In a conversation that drags on (thirty, forty exchanges), you may see the model let one or two rules go. The reason is mechanical: the model works with a limited context window and naturally gives more weight to the most recent messages than to the instructions at the start. Four habits are enough:
- Keep the system prompt short and prioritized. Past 400 or 500 words, rules get diluted and start contradicting each other.
- Number your rules. You'll be able to say ‘you skipped rule 3' instead of re-explaining everything.
- Phrase things positively when you can. ‘Use short sentences' works better than ‘don't write long sentences'.
- Open a new conversation for a new task instead of piling fifteen topics into the same thread. That's the basic principle behind context engineering: a clean, short context beats a long, cluttered one.
Method 1: build and test your system prompt in Skilzy's AI Lab
The fastest way to know whether your system prompt holds up is to test it on several requests in a row in one place, instead of guessing.
That's what the AI Lab built into Skilzy is for: you write your system prompt once, run several typical requests against it back to back, and adjust the rules that don't hold. Usage credits are included, so you don't need an extra subscription to run these tests. It's especially useful for system prompts, because not every rule holds the same way: your 20-words-per-sentence limit may be followed to the letter while your banned-vocabulary rule slips by the third message.
On the learning side, the Prompting Basics program walks through the build step by step: you start from an empty system prompt, add the five blocks one at a time, and watch live what each addition changes in the answer. The exercises use real cases (writing assistant, customer follow-up assistant, email-triage assistant), and you walk away with reusable system prompts, not lecture notes.
Two state-recognized, funding-eligible certifications (RS7439 for AI content marketing, RS6792 for AI and sales) are available if you want a more formal framework.
The limitation worth stating plainly: if all you need is to lock three style rules into ChatGPT for your emails, the tool's built-in feature is plenty. That's method 2.
Method 2: ChatGPT's custom instructions
ChatGPT has a free, permanent system prompt built in: custom instructions, which apply automatically to all your new conversations.
The path: open settings, then the Personalization section, then Custom instructions. You'll find two fields there. The first is for describing yourself (job, industry, audience, constraints). The second is for describing how you want the answers (length, tone, format, things to avoid). OpenAI's official documentation on custom instructions covers how they work and the cases where they don't apply.
In practice, put your role and context blocks in the first field, and your rules, format, and guardrails blocks in the second. The fields are short (around 1,500 characters each), which forces a healthy discipline: keep the rules that actually cost you time when they're ignored.
Two limits to keep in mind. First, these instructions apply everywhere, including when you're asking for a cake recipe: an over-specialized system prompt gets in the way outside its domain. Second, they don't travel backward in time, so your older conversations carry on without them. For framing that only concerns one specific project, use a ChatGPT project instead: you write instructions there that apply only to that project's conversations, which keeps the rest clean. If you're just getting started with the tool, the guide on how to use ChatGPT as a beginner walks through the interface in order.
Method 3: Claude projects, Gemini Gems, and the system parameter
Claude, Gemini, and APIs each offer their own version of the system prompt, with one clear advantage: framing per use case rather than one global setting.
In Claude, you create a project and fill in its instructions. Everything you write there applies to every conversation in the project, and you can attach reference documents (style guide, price list, approved sample texts). It's the most comfortable format when you're juggling several accounts in parallel: one project per client, one system prompt per project.
In Gemini, the equivalent is called a Gem. You name it, give it its instructions, and call it up when you need it. Same principle, but with the logic of named assistants rather than workspaces.
On the technical side, if you go through an API or an automation tool like n8n, the system prompt is a dedicated field called system, separate from user messages. Anthropic's documentation on system prompts explains why that separation matters: what you put in the system field is treated as a frame, not as a negotiable request. It's also where you can slip in two or three examples of ideal answers, a technique covered in our article on few-shot prompting.
One piece of advice that holds for all three: write your system prompt in a text file of your own, and copy it into the tool. Interfaces change, your rules stay, and you can reuse them elsewhere in thirty seconds.
Key takeaways
A system prompt is five blocks (role, context, rules, format, guardrails), under 400 words, with measurable, numbered rules and a stable place to store it. Start small: take the task you repeat most often this week, write the five blocks, install them in your tool's instructions, and fix one rule every time an answer disappoints you. After three or four rounds, you'll have a frame that saves you real time, every day, without ever re-explaining a thing.
