Classify · Transform · Writing & Content

Classify email subject lines and assign the right precursor

A pure function precursor_for(intent) that maps an email intent code to the canonical subject-line precursor string, graded on hidden intent->precursor cases.

You receive: A pure function: precursor_for(intent: string) -> string, where intent is one of {decision, action, feedback, fyi} and the output is the exact canonical precursor with trailing colon.

Part of Pitch Investors

What's verified: STUD verifies the function returns the exact canonical precursor string for each intent code and handles the unknown branch as configured, across hidden cases. STUD does NOT judge whether the subject line is good, whether the chosen intent matches the email's real purpose, or anything about the email body.

Opens soon

Cost20 credits

AcceptanceAutomated check against your inputs

ProtectionHeld until verified delivery

This objective is verified and ready. It opens soon, once sign-in and payments are live.

Deliverable interface

The exact vocabulary the automated check enforces: keys, tokens, entry points, and worked examples. Generated from the verification source.

{
 "constants": {},
 "entryName": "precursor_for",
 "expectNote": "expect is the comparison-space value (your return value goes through normalize first when one is published)",
 "hiddenCaseCount": 11,
 "hiddenCaseNames": [
  "v0",
  "v1",
  "v2",
  "v3",
  "v4",
  "v5",
  "v6",
  "error_token",
  "case_sensitive",
  "feedback_upper",
  "spaces_decision"
 ],
 "inputKeys": [
  "case_insensitive_intent",
  "intent_to_precursor",
  "unknown_behavior"
 ],
 "normalizeSource": "def _normalize_email_subject_precursor(r): return r if not isinstance(r, dict) else {\"precursor\": r.get(\"precursor\")}\n",
 "returnShapes": [
  [
   "precursor"
  ]
 ],
 "signature": "def precursor_for(inp):",
 "submission": "python exposing the entry function; inp is one input object; graded on held-out cases",
 "tier": "calculator",
 "visibleCases": [
  {
   "expect": {
    "precursor": "Decision:"
   },
   "input": {
    "case_insensitive_intent": "yes",
    "intent_to_precursor": "decision",
    "unknown_behavior": "empty"
   },
   "name": "decision"
  },
  {
   "expect": {
    "precursor": ""
   },
   "input": {
    "case_insensitive_intent": "yes",
    "intent_to_precursor": "reminder",
    "unknown_behavior": "empty"
   },
   "name": "unknown_empty"
  }
 ],
 "vocabulary": [
  "1",
  "Action Required:",
  "Decision:",
  "Feedback:",
  "For Your Information:",
  "INVALID",
  "action",
  "case_insensitive_intent",
  "decision",
  "empty",
  "feedback",
  "fyi",
  "intent_to_precursor",
  "precursor",
  "true",
  "unknown_behavior",
  "y",
  "yes"
 ]
}

Get early access to STUD the day it goes live.