You give ChatGPT an instruction, it follows it properly for three messages, and then it drifts back into its usual style. That is 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, a set of rules, an output format. The model keeps it in view at every turn, which makes it far more stable than a sentence tossed in halfway through.
Here you will 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 will also see why rules sometimes start slipping in long conversations, and the simple habits that fix most of those cases. No technical skills required: everything 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 best 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 recited the job description to before every single request would find you very strange. An AI, on the other hand, needs exactly that, and it is precisely what the system prompt does: the model 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 are 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 with 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 is 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 safeguards. If one is missing, that is almost always where the AI goes off the rails.
| Block | The question it answers | Short example |
|---|---|---|
| Role | Who is speaking? | You are a copy editor for an accounting firm. |
| Context | For whom, in what setting? | Our readers are small-business owners with no accounting background. |
| Rules | What to do, what to avoid? | Sentences of 20 words maximum, no jargon. |
| Format | What does a good answer look like? | One heading, three paragraphs, a three-point list. |
| Safeguards | What to do when in doubt? | If a detail is missing, ask instead of inventing it. |
Here is 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 private individuals having a custom staircase or bookcase installed. Project budgets range from €4,000 to €12,000. They usually compare three quotes before choosing.
Rules: write in English, addressing the customer courteously and professionally. Sentences of 20 words maximum. 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-point list, a one-line call to action.
Verification: if information is missing (dimensions, type of wood, access constraints), ask me instead of making it up. At the end of the message, flag any rule you were unable to follow.
That prompt is under 150 words and yet it removes most of the corrections you would otherwise make by hand. Three details do the work: the rules are countable and checkable (“20 words maximum” 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 paper over 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 Slipping
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 ordered by priority. Past 400 or 500 words, the rules dilute and start contradicting each other.
- Number the rules. You will be able to say “you skipped rule 3” instead of explaining everything again.
- 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 is 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 construction 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 are based on 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, fundable certifications (RS7439 for AI content marketing, RS6792 for AI and sales) are available if you want a more formal framework.
The limitation worth knowing, and it's only fair to say it plainly: if all you need is to lock in three style rules in ChatGPT for your emails, the tool's native feature is more than enough. That is 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 will 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, 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 (roughly 1,500 characters each), which forces a healthy discipline on you: keep the rules that genuinely cost you time when they aren't 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 becomes a nuisance outside its domain. Second, they don't travel back in time, so your older conversations carry on without them. For framing that only concerns one specific project, use a ChatGPT project instead: there you write instructions that apply only to that project's conversations, which avoids polluting everything else. If you are just starting out 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, examples of approved copy). It is the most comfortable format when you are juggling several accounts at once: one project per client, one system prompt per project.
In Gemini, the equivalent is called a Gem. You name it, you give it its instructions, and you call it up when you need it. The principle is the same, 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 is also where you can slip in two or three examples of ideal answers, a technique detailed 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 somewhere else in thirty seconds.
Key Takeaways
A system prompt is five blocks (role, context, rules, format, safeguards), 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 iterations, you will have a frame that saves you real time, every day, without explaining anything twice.
