Generates a full XML prompt from a natural language instruction, or iteratively refines an existing prompt when conversationHistory and existingPrompt are supplied. Does not persist anything; the returned prompt text is meant to be saved by the caller.
Documentation Index
Fetch the complete documentation index at: https://docs.tetherai.ca/llms.txt
Use this file to discover all available pages before exploring further.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Natural-language ask describing what the prompt should accomplish.
Optional current prompt XML to iteratively refine; absent for first-draft generation.
Prior turns in this prompt-drafting session, replayed so the model can continue an iterative refinement thread.
Available runtime variables and field scopes (grouped) the editor exposes; constrains the model to real @variables instead of inventing placeholders.
When true, drafting uses the stronger battle-tested XML architecture system prompt; otherwise stays closer to the user request with lighter guardrails.
Pin to a specific provider/model (e.g. { provider: 'anthropic', model: 'claude-sonnet-4-6' }) overriding the org's default assignment.
{
"provider": "anthropic",
"model": "claude-sonnet-4-6"
}