Skip to content
Pip Decks AI Building Bootcamp

System Prompts

Coding agents come with their own system prompts. Claude Code has its own, Cursor has one, Codex has one, and so on. Some of these companies actually publish their system prompt so you can view it. Others do not, but there are accounts on Twitter that go and trick the system to expose its own system prompt. So you can always go and look at them.

Effectively, what they say is, “You are an expert software engineer. These are the things you can do. These are the things you shouldn’t do. This is the company that created you. Your knowledge cutoff is this date, but it is currently this date.” (because LLMs have knowledge only up to a certain date).

Coding agents can use web search tools, so they can get up-to-date information. They also might include a reference to their own documentation. So if you’re asking, “How do I set this thing up in my coding agent?” it can look at its own documentation to guide you (or do it for you).

What’s in a System Prompt?

Section titled “What’s in a System Prompt?”

A typical system prompt includes:

  • Identity: Who the agent is and what company made it
  • Capabilities: What tools and actions it can take
  • Limitations: What it should avoid doing
  • Knowledge cutoff: When its training data ends
  • Current date: So it knows what “today” means
  • Behavioral guidelines: How to respond, format code, etc.

The system prompt is the foundation that shapes how the agent behaves before you ever type a single message.

Section titled “Related Resources”