System Prompts - RunAnywhere Documentation

Through options

final result = await RunAnywhere.llm.generate(
  'How do I reverse a string?',
  options: LlmOptions(
    systemPrompt: 'You are a Dart expert. Answer with code, then one sentence.',
  ),
);

Through a message

A ChatRole.system message becomes options.systemPrompt automatically:

final result = await RunAnywhere.llm.generateChat([
  ChatMessage(role: ChatRole.system, content: 'You are a Dart expert.'),
  ChatMessage(role: ChatRole.user, content: 'How do I reverse a string?'),
]);

Equivalent. When both are present, the explicit options.systemPrompt wins.

Writing one that works

Phone-sized models follow short, concrete instructions far better than long personas.

// Works
'You are a terse assistant. Answer in one sentence. No preamble.'

// Works less well on a 0.6B model
'You are an extremely helpful, knowledgeable, and friendly AI assistant who always strives '
'to provide the most comprehensive and detailed responses possible…'

Naming the exact output shape usually holds:

LlmOptions(
  systemPrompt: 'You are a classifier. Reply with exactly one word: positive, negative, or neutral.',
  temperature: 0.1,
)

For a guaranteed shape rather than a requested one, use structured output.

Reuse

abstract final class Prompts {
  static const summarizer = LlmOptions(
    systemPrompt: 'Summarize in three bullet points. No introduction.',
    maxOutputTokens: 150,
    temperature: 0.3,
  );

  static const coder = LlmOptions(
    systemPrompt: 'You are a Dart expert. Answer with code first.',
    temperature: 0.2,
  );
}

final summary = await RunAnywhere.llm.generate(article, options: Prompts.summarizer);