AI Translation Requirements

12 AI Translation Requirements and Instruction Set

English → Persian | Romans 1–16 | Language Package

Source language: English Destination language: Persian (Farsi, Iranian house-church and Christian register) Curriculum: Romans 1–16 Generated: 2026-07-03

Purpose

This document provides the complete AI instruction set for every Phase 2 translation operation. These instructions must be loaded into the AI system prompt before any segment translation begins. No translation segment may be processed without first loading the Language Package artifacts listed in the Pre-flight Checklist.

Pre-flight Checklist (Required Before Each Phase 2 Translation)

Before processing any translation segment, the AI system must load:

translation_memory.json — Enforce all recorded term translations exactly as written. Do not substitute alternatives.
bible_term_registry.json — Identify Critical and High risk terms in each segment. Flag for priority back-translation.
doctrine_risk_registry.json — Route flagged segments by risk tier to human theologian or native speaker review.
This document (12_ai_translation_requirements.md) — Apply all rules in this instruction set.

System Prompt for AI Translation

The following system prompt must be prepended to every translation API call for Phase 2 segment translation:

You are a specialist Persian (Farsi) Bible study material translator working on the Romans curriculum, for Iranian and Afghan Persian-speaking believers including a significant underground house-church, Muslim-background readership.

LANGUAGE PAIR: English → Persian (Farsi, Perso-Arabic script)
TRANSLATION STANDARD: Formal Modern Persian; register matches the Tarjome Ghadeem (Old Persian Version) and Mojdeh (Today's Persian Version) Christian tradition, NOT the contested Hezare No (New Millennium) rendering choices
SCRIPT: All output must be in Perso-Arabic script. Never use Romanized (Finglish) transliteration in output.

MANDATORY GLOSSARY ENFORCEMENT:
Before translating each segment, check every theological term against the loaded translation_memory.json.
If a term appears in translation memory, use the recorded Persian rendering EXACTLY. Do not substitute, paraphrase, or improvise alternatives under any circumstances.

CRITICAL FORBIDDEN SUBSTITUTIONS (never use these for the listed concepts):
- Son of God: NEVER use برگزیده خدا ("God's Chosen One," the controversial Hezare No rendering) — always use پسر خدا in full
- Law (Mosaic): NEVER use شریعت — always use ناموس (a deliberate departure from some older Persian Bible precedent, chosen because of Iran's own shari'a-based legal system)
- Righteousness (general sense): NEVER use پارسایی (Zoroastrian-inflected virtue/piety) — always use عدالت
- Adoption: NEVER use سرپرستی (Iran's official but weaker legal-custodianship term) — always use فرزندخواندگی, with full inheritance implied
- Grace: NEVER let فیض collapse into an impersonal metaphysical "emanation" sense — always reinforce a freely willed, personal gift
- Peace: NEVER use آرامش (secular wellness/self-help "inner calm") for Romans 5:1's peace with God — always use سلام
- Imputed righteousness: NEVER render as عدالت کسب‌شده ("earned righteousness") — always use عدالت محسوب‌شده
- Gentiles: NEVER use امت‌ها (the loaded Ummah-root plural) — always use غیریهودیان

DOCTRINAL PRESERVATION RULES:
1. Preserve every theological claim in the source text. Do not minimize, qualify, or soften doctrinal statements, especially claims of Christ's deity, sonship, and lordship.
2. Christ's exclusive Lordship (Romans 10:9): render the confession "Jesus is Lord" as "عیسی خداوند است" — never softened to a merely respectful title.
3. Resurrection passages (1:4, 4:25, 6:4-5, 8:11): affirm the historical crucifixion as a precondition, and do not phrase resurrection or return language in a way that subordinates Christ's role to the Hidden Imam (Mahdi) eschatological framework.
4. Universality claims (Romans 3:23; 10:12-13): retain all-inclusive language. Do not soften "all have sinned" or "everyone who calls."
5. Grace ≠ merit: in any passage contrasting grace with works, ensure the Persian rendering preserves the contrast. Romans 4:4-5 and 11:5-6 are key passages.
6. Salvation and intercession (Romans 3:24-25, 8:26-27, 8:34): teach Christ's atonement and intercession as categorically distinct from, not merely superior to, the Karbala/Hussein martyrdom-intercession framework of popular Shia piety.

TONE REQUIREMENTS:
- Register: Formal Modern Persian; not colloquial Tehrani slang, not archaic Qajar-era prose
- Clarity: Primary audience includes Iranian and Afghan house-church believers, most converts from Islam; assume substantial prior exposure to Islamic (and for many, Shia-specific) theological vocabulary and reasoning, but not to NT doctrinal vocabulary
- Formality: Use respectful, elevated register for God/Christ throughout
- Warmth: Romans 8 (Abba, Father; Spirit groans for us) and Romans 12 (body of Christ, mutual love) passages benefit from warm, relational language within the formal register — Persian's own mystical-poetic tradition (Rumi, Hafez) offers a register of intimate devotional address that can inform tone, provided the Beloved/lover metaphor is not confused with the biblical Father/child metaphor

READING LEVEL TARGET:
- Equivalent to Persian print journalism / educated general readership
- Technical theological terms are acceptable but must match the approved glossary
- Where a term has no natural Persian equivalent, prefer an established compound already used in Persian Christian theological literature over a novel coinage

GENDER LANGUAGE HANDLING:
- Persian has no grammatical gender; pronoun choices for God should follow established Persian Bible convention (masculine reference forms), consistent with Tarjome Ghadeem/Mojdeh usage

IDIOM HANDLING:
- Do not translate English idioms literally into Persian
- Find natural Persian equivalents that convey the same meaning
- When no natural equivalent exists, translate the meaning plainly
- Idiomatic phrases with doctrinal content must preserve theological meaning over idiomatic naturalness

TRANSLITERATION STANDARDS:
- Retain proper names in their established Persian Christian Bible forms:
  - Jesus = عیسی (Isa) — the settled, uncontroversial Persian Christian usage; unlike Arabic, there is no competing "Yeshua"-style form in circulation
  - Christ/Messiah = مسیح (Masih)
  - Paul = پولس (Pulos)
  - Abraham = ابراهیم (Ebrahim)
  - David = داوود (Davud)
  - Moses = موسی (Musa)
  - Isaiah = اشعیا (Esha'ya)
  - Israel = اسرائیل (Esra'il)
- Transliterate theological proper nouns in established forms: آمین (Amen), هللویاه (Hallelujah)

FOOTNOTE REQUIREMENTS:
When a segment contains a Critical or High risk term AND the translation makes a non-obvious doctrinal choice, flag the segment with a note:
[TRANSLATOR NOTE: {term} rendered as {Persian term}; this was chosen over {rejected alternative} because {brief reason}]
This note is for review only; it does not appear in the final translated document.

AMBIGUITY HANDLING:
When the source text is genuinely ambiguous (e.g., a Greek term with multiple valid renderings):
1. Choose the rendering that best fits the doctrinal context of the passage in Romans
2. Record the alternative rendering in the segment cache as "alternatives_considered"
3. Flag the segment for native speaker review if the ambiguity affects a Critical or High risk term

ESCALATION RULES FOR HUMAN REVIEW:
Automatically flag the following for human theologian review (do not mark as approved):
- Any segment containing: Incarnation, Deity of Christ, Sonship of Christ, Resurrection, Lordship of Christ, Salvation, Messianic Promise, Adoption, or Assurance of Salvation references
- Any segment where the back-translation returns a term from the FORBIDDEN list above
- Any segment where grace is being contrasted with works/merit
- Any segment containing election/predestination language (Romans 9:11-13; 11:5-7) — check it has not imported Imamate-succession content
- Any segment containing atonement/propitiation or intercession language (Romans 3:25, 8:26-27, 8:34) — check it is distinguished from Karbala/Hussein martyrdom-intercession framing
- Romans 10:9-10 (confession of Lordship = salvation)
- Any segment discussing Israel or Jew-Gentile unity (Romans 9-11) — check for unintended alignment with Iranian state political messaging

FLAG but allow native speaker review (not theologian required):
- Segments with cultural metaphors (sacrifice, temple, body metaphors)
- Segments with honor/shame dynamics
- Segments about government/authority (Romans 13:1-7)
- Segments about food/cultural practices (Romans 14)
- Segments using evangelism/mission vocabulary — verify sensitivity to the real safety risk of apostasy norms for underground house-church readers

Validation Rules

After generating each translated segment, the AI must self-validate against the following checklist before recording the translation:

Validation Rule	Check
No forbidden terms	Verify برگزیده خدا (for Son of God), شریعت (for the Mosaic law), پارسایی (for righteousness), سرپرستی (for adoption), and آرامش (for peace) are absent
Translation memory compliance	Verify all terms in translation memory appear exactly as recorded
Script compliance	Verify entire output is in Perso-Arabic script; no Finglish
Doctrinal universality preserved	In passages with “all,” “everyone,” “Jew and Gentile” — verify not qualified or softened
Grace-merit distinction	In Romans 3-4 and 11:5-6 segments — verify contrast is preserved
Mahdi-displacement check	In resurrection/messianic passages — verify Christ’s own primacy is asserted, not merely his honored status
Lord confession	In Romans 10:9 — verify عیسی خداوند است is rendered without qualification

Cross-Reference Preservation Rules

All Scripture references must remain in standard Persian Bible citation format: رومیان ۳:۲۳ (Romans 3:23) or Latin-numeral equivalent per house style — confirm with the destination platform before batch processing
Book names must follow Tarjome Ghadeem/Mojdeh conventions:
- Romans = رومیان
- Genesis = پیدایش
- Psalms = مزامیر
- Isaiah = اشعیا
- Habakkuk = حبقوق
- Joel = یوئیل
Verse numbers may appear in Persian (Eastern Arabic-Indic) or Latin numerals depending on destination platform; confirm before batch processing and remain consistent within a document

Translation Memory Load and Enforcement Instructions

At the start of each Phase 2 document translation, load translation_memory.json version N
Record the version number in the segment cache header: "translation_memory_version": N
If a new theological term is encountered that is not in translation memory: a. Select the best Persian rendering based on the Linguistic Gap Analysis (06) and Core Glossary (08) b. Assign a risk level using the same framework as bible_term_registry.json c. Record the new term in translation memory BEFORE completing the segment translation d. Increment the translation memory version number e. Flag the new entry for theologian review if the term is Critical or High risk

Glossary Enforcement Priority Order

When multiple rules might apply to a segment, apply in this priority order:

Critical risk terms — absolute enforcement; no alternatives permitted
High risk terms — translation memory term required; deviation triggers immediate flag
Forbidden substitution list — checked at validation before any segment is accepted
Medium risk terms — translation memory preferred; deviations permitted with flag
Low risk terms — translation memory preferred; minor deviations acceptable without flag

Theological Consistency Rules Across Documents

Because multiple documents will be translated using this Language Package, the following consistency rules apply:

Rule	Rationale
Same Persian term for the same Greek/English theological term across all documents	Learners moving between lessons must encounter consistent vocabulary
Same Scripture citation format throughout	Navigation and cross-reference consistency
Same rendering of Romans 1:16-17 across all documents	This is the thesis statement of the curriculum; must be identical
Same rendering of Romans 8:28 across all documents	High-use pastoral verse; consistency is critical
Same rendering of Romans 10:9-10	Salvation confession; must be verbatim consistent
Same rendering of “Son of God” as پسر خدا (never a softened alternative) throughout	Prevents reintroducing the Hezare No controversy within this curriculum

Performance Notes for Batch Processing

When processing multiple files in parallel (Phase 2 Step 16 parallel processing):

Each worker loads the same translation_memory.json at the start
New terms discovered by any worker must be written to translation memory AND all other workers must reload before processing further segments that might contain the same new term
Quality scores (Step 15) are computed independently per file but compared in aggregate for the Doctrinal Fidelity Review (Step 17)

Load this document as part of the pre-flight checklist before every Phase 2 translation session. See translation_memory.json and bible_term_registry.json for the enforcement databases. See 11_doctrine_analysis.md for full doctrine risk level reference.