pub fn bootstrap_prompt(persona_description: &str) -> StringExpand description
Generate a calibration prompt for bootstrapping a persona lexicon via an LLM.
Pass the returned string to any LLM. The model’s response will be a fenced TOML
block suitable for parsing with [super::ConfigLexiconScorer::from_str] or saving
to disk for super::ConfigLexiconScorer::from_file.
CF provides the calibration baseline; the caller is responsible for making the LLM call and persisting the result. Extract the TOML from inside the fenced block before parsing.
§Example
use context_forge::lexicon::bootstrap_prompt;
let prompt = bootstrap_prompt("A Space Marine Chaplain from Warhammer 40k");
assert!(prompt.contains("Space Marine Chaplain"));
assert!(prompt.contains("0.0, 1.5]"));