Context Engineering
System Prompts
The system prompt is persistent context the model reads before every user interaction: it sets the agent's role, behavior boundaries, output format, and decision-making rules, functioning as the agent's standing instructions that govern all subsequent reasoning. Well-designed system prompts specify what the agent should and should not do, include examples of desired behavior, and give the model a clear framework for handling ambiguous situations without asking for clarification. The gap between a mediocre agent and a production-grade one often comes down entirely to system prompt quality, because every inference the model makes runs through this foundational context.
connected to
resources
Anthropic: System Promptsdocs.anthropic.comOfficial guidance on writing effective system prompts for Claude (docs.anthropic.com)Anthropic's Claude System Promptdocs.anthropic.comAnthropic's published production system prompt showing production-grade design (docs.anthropic.com)OpenAI: System Message Best Practicesplatform.openai.comOpenAI's recommended patterns for system messages (platform.openai.com)Awesome Cursorrulesgithub.comReal-world system prompt examples from the developer community (github.com)