Instructions: The invisible rules

Before you write the first word to an AI, rules for the conversation are already in place. Alongside your prompt, so-called system or developer instructions can define in the background how the system should behave. They influence tone, safety boundaries and basic behavioural patterns.

This often makes answers polite, structured and predictable. But the same guardrails can also contribute to responses that feel more cautious, polished or accommodating than you actually need in everyday use.

The invisible corset

The behaviour of modern AI assistants never comes from your prompt alone. Training, safety mechanisms and higher-level instructions also shape the response:

• The pleasing mode: AI systems can tend to confirm the user’s view or judge ideas more favourably than the facts justify. This behaviour is known as sycophancy. If you mostly receive agreement, weaknesses may become harder to notice.
• The appearance of consensus: On controversial questions, models often produce balanced “on the one hand / on the other hand” answers. That can be useful – but it becomes an obstacle when you are looking for a clear assessment or a genuine counter-position.
• Unrequested baggage: Depending on the model and its settings, responses may include opening phrases such as “I’d be happy to help …”, additional caveats or summaries even when you never asked for them.

Your leverage in everyday use

• Use your own instructions: Many major AI assistants allow you to set persistent preferences or custom instructions. They do not override the provider’s higher-level rules, but they can strongly influence how the AI writes, structures answers and works with you.
• Don’t just say what – say how: Define the role you want the AI to take and the kind of disagreement you expect. For example:

“Act as my critical sparring partner. Examine my assumptions logically. If an idea has weaknesses, name them directly and without flattery. Avoid greeting phrases and unrequested summaries.”

The key point: Your prompt is never the only instruction in the room. Invisible rules shape every answer – and your own instructions let you consciously influence part of those rules.