Response Priming

It is possible to provide the start of the LLM response (assistant message) in the script. This allows to steer the answer of the LLM to a specify syntax or format.

Use writeText with the {assistant: true} option to provide the assistant text.

$`List 5 colors. Answer with a JSON array. Do not emit the enclosing markdown.`

// help the LLM by starting the JSON array syntax
// in the assistant response
writeText(`[`, { assistant: true })

👤 user

List 5 colors. Answer with a JSON array. Do not emit the enclosing markdown.

🤖 assistant

"red",
"blue",
"green",
"yellow",
"purple"
]

How does it work?

Internally when invoking the LLM, an additional message is added to the query as if the LLM had generated this content.

{
  "messages": [
    ...,
    {
      "role": "assistant",
      "content": "[\n"
    }
  ]
}