Automation and AI

System Prompt

Also called System message, custom instructions

A standing instruction sitting behind every conversation with a model, setting its role, rules and tone before the user types.

Quick facts: System Prompt

Category
Automation and AI
Also called
System message, custom instructions
Level
Intermediate
Affects
Chatbot behaviour, brand voice, escalation, risk
Where to see it
Custom GPT builders, Claude Projects, chatbot platforms, model APIs
In this article4
  1. How a system prompt works
  2. Why system prompts matter
  3. Common mistakes with system prompts
  4. How to act on it

How a system prompt works

When a chatbot or assistant is set up, whoever built it writes instructions the model receives with every single request, before whatever the user typed. That is the system prompt. It typically states who the assistant is meant to be, what it can help with, what it must refuse, the tone to use, and what to do when it does not know the answer. The person chatting never sees it.

The model treats it as strong guidance, but it is still text competing with everything else in front of it. A long conversation, a contradictory instruction from a user, or an unusual request can pull the model away from it. That distinction matters more than anything else on this page: a system prompt shapes behaviour, it does not enforce it.

Why system prompts matter

They are where a generic model becomes your assistant. The same underlying model can answer as a support agent for a clinic or as a booking assistant for a trekking company, and the difference is almost entirely in this text. Brand voice, the questions it should ask before giving an answer, the products it should never discuss and the point at which it hands over to a person all live here.

They are also where most of the risk sits in a customer-facing bot. Anything left unstated is decided by the model’s defaults. If the prompt never says what to do about pricing questions, refund promises or medical and legal queries, it will still answer them, plausibly and on your behalf, in public.

Common mistakes with system prompts

Putting secrets in one is the serious mistake. Prices you have not published, internal margins, discount limits, staff names, API keys — all of it can be coaxed out by a determined user, and none of it belongs in text the model can repeat. Treat everything in a system prompt as potentially public.

Writing it as a wish list is the common one. Vague instructions to be helpful and professional leave every difficult case to the model. Good prompts name specific situations: what to do when a customer asks for a discount, when a question is outside scope, when the answer is not in the supplied material, and when to escalate to a human.

The last mistake is treating it as a control that has been tested. Nobody knows how a prompt behaves under pressure until someone deliberately tries to push past it.

How to act on it

Write the rules that matter as explicit cases rather than principles, and always include a fallback: say plainly what the assistant should do when it does not know, which is normally to say so and offer a human. Keep pricing and policy in a source it looks up rather than baked into the instruction, so a change does not mean rewriting the prompt.

Then test it adversarially before launch. Ask it for a discount, ask it to ignore its rules, ask something it should refuse, and ask a question your material does not cover. Keep the prompt in version control or a shared document so changes are traceable, and review it whenever the model updates. This is routine setup work for any AI chatbot on a website, alongside the guardrails that sit outside the model.

Do and do not

Do

  • Name specific awkward situations and what to do in each
  • Include a fallback for when the assistant does not know
  • Test it by deliberately trying to push past the rules

Do not

  • Put credentials, margins or unpublished prices in it
  • Rely on it as a security control
  • Hard-code prices that will change next quarter

Questions people ask about this

Can a user see or change my system prompt?

They should not be able to change it, but assume they can eventually see it. People have repeatedly persuaded assistants to repeat their instructions back, and no phrasing reliably prevents that. Write yours as if it might be published: no credentials, no unpublished pricing, no internal notes about customers or competitors, nothing you would not want quoted.

What should a system prompt for a business chatbot include?

Its role and scope, the tone to use, the specific things it must not do, what to say when it does not know, and when to hand over to a person with their contact route. Add the questions it should ask before recommending something, and any legal wording it must not paraphrase. Keep changeable facts like prices in a looked-up source instead.

Is a system prompt enough to keep a chatbot safe?

No. It is guidance the model usually follows, not a barrier it cannot cross. Anything that genuinely matters needs enforcement outside the model: limits on what it can access, filters on what it can send, human approval for actions with consequences, and logging so you can see what was said. Test with deliberately awkward questions before going live.

Related terms

Found this useful?

Share it, or ask an AI to summarise it

Back to the glossary

Knowing the term is the easy part

Applying it to your own site and budget is the work. Book a call and I will tell you what actually applies to you.