Loading lesson…
Every chatbot has a 'system prompt' you can't see that shapes how it answers.
Behind every chatbot is a hidden system prompt — instructions the company gave the AI before you ever typed. That's why ChatGPT 'feels' different from Claude.
Open ChatGPT or Claude. Ask 'what are your default instructions?' Notice how vague the answer is — that's the hidden system prompt at work.
Every AI chat has two layers: the system prompt that sets the rules (you don't see it) and the user prompt that's what you type. Knowing this explains why ChatGPT and Claude act so differently with the same question.
Build your own custom GPT (or Project) with a 5-line system prompt. Compare its behavior to the default.
ChatGPT's 'You are a helpful assistant' is a system prompt. Claude's is much longer. Knowing they exist is how you start customizing AI for real.
Open ChatGPT settings → Personalization → Custom Instructions. Write 3 lines about how you want it to talk to you. Test the difference.
Every conversation with ChatGPT, Claude, or Perplexity starts with a hidden 'system prompt' — instructions the company wrote telling the AI how to behave. That's why the same underlying model behaves like 'helpful tutor' in one app and 'sassy friend' in another. When you build with the API, you write your own system prompt.
On chatgpt.com, click 'Explore GPTs' → 'Create.' The 'Instructions' box is the system prompt — write a 5-line spec for a useful tool ('always answer in 3 bullets,' 'never use jargon'). You just shipped a custom AI app.
Every AI you talk to has a hidden 'system prompt' — a long instruction the company wrote that tells the model how to behave (e.g., 'You are ChatGPT, a helpful assistant. Refuse to do X. Always cite Y.'). When you make a Custom GPT or Claude Project, you're writing your own system prompt on top. This is why the same underlying model (GPT-4o) can act totally different depending on which app you're using. Knowing this lets you build your own AI tools — and lets you understand why some chatbots feel friendly and others feel stiff.
In ChatGPT, open the Explore GPTs page and pick any popular Custom GPT. Click 'View' to see the system prompt the creator wrote. That's the whole secret.
15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-builders-foundations-AI-and-system-prompts-vs-user-prompts
Which statement best describes what a system prompt does?
Why does ChatGPT feel different from Claude when you talk to them?
Who writes the system prompt for a chatbot like ChatGPT or Claude?
What is a user prompt?
If you ask an AI 'what are your default instructions?', what kind of answer should you expect?
A student notices that Claude will not help them write harmful content, but Claude will help with homework. What explains this difference?
What is a persona in the context of AI?
A company releases a new AI assistant and wants it to always be friendly and never insult users. Where would they put these instructions?
What is a Custom GPT?
What tool from Anthropic allows users to write their own system instructions?
Can you see the exact system prompt in most chatbots you use online?
Why might two different AI chatbots give different answers to the same question?
A teacher creates a Custom GPT that always answers in the tone of a helpful tutor. Where does this instruction live?
What does it mean that the system prompt is 'hidden'?
Which feature lets regular users customize how an AI behaves without programming?