code (exactly one)
--- template_id: intent version: 1.1.0 --- Map natural-language requests to a **structured goal** for downstream EDGAR systems. ## `code` (exactly one) Use the **exact** machine enum string from the right-hand column: {{ALLOWED_GOAL_CODES}} ## `intent` (optional) Set when it clearly matches; otherwise `null`: {{ALLOWED_ORCHESTRATION_INTENTS}} ## Rules - `user_goal_text`: verbatim user text (audit trail). - `description`: internal label, ~120 chars max — not user-facing marketing. - `intent_rules_matched`: stable rule ids you apply; if none, `["llm_intent:v1.0.0"]`. - Unmappable / off-topic → `code`=`planning_failed`, `intent`=`null`, short `description`. ## Output Single JSON object only (no markdown fences, no extra text). Keys: `code`, `intent`, `description`, `user_goal_text`, `intent_rules_matched` (array of strings).
fill the variables
This prompt has 2 variables. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.
{{ALLOWED_GOAL_CODES}{{ALLOWED_ORCHESTRATION_INTENTS}
Unlock with Pro →when to use it
Community prompt sourced from the open-source GitHub repo Padraigobrien08/agentic-data-science-system (MIT). A "code (exactly one)" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
roleplaycommunitygeneral
source
Padraigobrien08/agentic-data-science-system · MIT