You give ChatGPT an instruction, it applies 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 even starts: a role, some context, rules, an output format. The model keeps it in view at every single 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 of those 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 must respect, and it stays active for every 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 re-read the entire job description to before every 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 at 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 (plus project instructions);
- in Claude, project instructions;
- in Gemini, Gems;
- on the developer side, a parameter named system sent with every request.
The concrete difference from a normal message: your message stays one item of history among dozens of others, whereas the system prompt is treated as a priority framing instruction. That's why a rule written in the right place holds 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 safeguards. When one is missing, that's almost always where the AI goes off the rails.
| Block | The question it answers | Short example |
|---|---|---|
| Role | Who's speaking? | You are a copy editor for an accounting firm. |
| Context | For whom, in what setting? | Our readers run small businesses and have no accounting training. |
| 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. |
| Safeguards | What to do when in doubt? | If a detail is missing, ask instead of inventing it. |
Here's a complete example, deliberately mundane and very specific, for a small business:
Role: you are a writing assistant for Atelier Vermeil, a craft joinery workshop in Nantes with two employees.
Context: our customers are homeowners having a custom staircase or bookcase built and installed. Project budgets run from €4,000 to €12,000. They usually compare three quotes before deciding.
Rules: write in English, addressing the customer politely. 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 topic allows.
Format: one heading, three 60-word paragraphs, a three-item list, a one-line call to action.
Check: if information is missing (dimensions, type of wood, access constraints), ask me instead of making it up. At the end of your message, flag any rule you weren't able to follow.
This prompt is under 150 words, and yet it removes most of the corrections you'd otherwise make by hand. Three details do the work: the rules are countable and verifiable (“20 words max” is measurable, “be concise” is not), the prohibitions are named explicitly, and the last block gives the AI permission to ask a question rather than fill a gap. To go further on how to phrase the instructions themselves, the complete method for writing a good prompt breaks down every building block.
When the rules start to slip
In a conversation that drags on (thirty, forty exchanges), you may see the model let go of a rule or two. 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 dilute 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 stacking fifteen topics in one thread. That's the basic principle of 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 see live what each addition changes in the answer. The exercises use real cases (a writing assistant, a customer follow-up assistant, an email triage assistant) and you walk away with reusable system prompts, not lecture notes.
Two state-recognized, fundable certifications (RS7439 for AI content marketing, RS6792 for AI and sales) are available if you want a more formal framework.
One limitation worth stating plainly: if all you need is to lock three style instructions into ChatGPT for your emails, the tool's native feature is more than enough. That's method 2.
Method 2: ChatGPT's custom instructions
ChatGPT ships with a free, permanent system prompt: 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. The first is for describing yourself (job, industry, audience, constraints). The second is for describing how you want the answers (length, tone, format, prohibitions). OpenAI's official documentation on custom instructions explains 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 safeguards blocks in the second. The fields are short (around 1,500 characters each), which forces a healthy discipline: keep the rules that genuinely cost you time when they're not followed.
Two limits to keep in mind. First, these instructions apply everywhere, including when you ask for a cake recipe: an overly specialized system prompt gets in the way outside its domain. Second, they don't reach back in time, so your older conversations carry on without them. For framing that only concerns one specific piece of work, use a ChatGPT project instead: you write instructions there that only apply to that project's conversations, which keeps the rest clean. If you're brand new to 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 the 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, 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 the user's messages. Anthropic's documentation on system prompts explains why that separation matters: whatever goes 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 your own text file, then 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, safeguards), under 400 words, with measurable and 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 iterations, you'll have a frame that saves you real time, every day, without ever re-explaining a thing.
