System Prompts - RunAnywhere Documentation

Through options

const result = await RunAnywhere.llm.generate('How do I reverse a string?', {
  systemPrompt: 'You are a TypeScript expert. Answer with code, then one sentence.',
})

Through a message

A system message becomes options.systemPrompt automatically:

const result = await RunAnywhere.llm.generate([
  { role: 'system', content: 'You are a TypeScript expert.' },
  { role: '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:

await RunAnywhere.llm.generate(review, {
  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

import type { LlmOptions } from '@runanywhere/core'

export const prompts = {
  summarizer: {
    systemPrompt: 'Summarize in three bullet points. No introduction.',
    maxOutputTokens: 150,
    temperature: 0.3,
  },
  coder: {
    systemPrompt: 'You are a TypeScript expert. Answer with code first.',
    temperature: 0.2,
  },
} satisfies Record<string, LlmOptions>

const summary = await RunAnywhere.llm.generate(article, prompts.summarizer)