System prompt
Instructions an app puts at the start of every request, before the conversation - who the assistant is, its rules, its style and its tools. Users rarely see it, but it is why the same model acts so differently in different apps.
Depth 1 · Foundation
You can say what a system prompt contains, where it sits in the context, and why it shapes behaviour strongly without being a security wall.
Sign in to prove what you know with a short quiz, see how deep you've gone, and earn XP for it.
Sign in with GoogleDepths of understanding
- 1
Foundation
You can say what a system prompt contains, where it sits in the context, and why it shapes behaviour strongly without being a security wall.
- 2
Deeper
You can build it: send standing instructions in the request's own system argument, apart from the conversation, and write one an agent can work by: who it is, how to work, what to distrust and when it's done.
Master depth 1 first
Your path here
What's still between you and System prompt, depth 1, in the order you can learn it.
- 1Language modelDepth 1 · Foundation · Language Models
- 2TokenDepth 1 · Foundation · Language Models
- 3ProbabilityDepth 1 · Foundation · Probability
- 4Next-token predictionDepth 1 · Foundation · Language Models
- 5Stateless modelDepth 1 · Foundation · Language Models
- 6Context windowDepth 1 · Foundation · Language Models
- 7System promptDepth 1 · Foundation · Language Models
Where it fits
Builds on
This concept