Skip to content

Translate Review

🤖 AI Drafted (Not reviewed)

Second-pass AI double-check of a draft translation against the original source: corrects mistranslations, omissions, and altered names. Target language, model, and prompt are editable.

Tool id text_translate_review
Category llm
Uses a language model yes
Needs a generative model no
Runs over many items yes
Item handling batch
Structured output yes
Human-verified not yet

What it reads

Port Type Required What it is
Draft translation (text) text yes The draft translation to review and correct.
Context (context) any no Previous text/transcription
Metadata (metadata) json no Existing metadata
Documents (documents) json no Document metadata

What it emits

Port Type Required What it is
Text (text) text Raw text response
Value (value) any Parsed value
Texts (texts) array Per-item texts
Values (values) array Per-item values
Results (results) json Full results
Records (records) array Per-document text records [{doc_id, text}, …].
Artifacts (artifacts) json Artifact IDs

Options

Option Type Default What it does
choices array Valid choices. (Not shown in the editor.)
chunk_size_chars integer 0 Chunk large input text above this character budget (0=auto).
match_mode string prefer Match mode. One of: prefer, strict, inform.
max_items integer 10 List max items.
max_tokens integer 8192 Max response.
max_words integer 50 Word limit.
metadata_field string Save to field.
model_name string Model name.
output_format string text Response format. One of: text, boolean, choice, number, words, list, json.
prompt string Custom prompt.
provider_name string LLM provider. One of: openai, anthropic, google, ollama, lmstudio, groq, together, deepseek, mistral, openrouter, dashscope, xai, perplexity, fireworks, deepl.
quality_gate boolean yes Stop the run if output is unreadable.
reference_values object Known values to match. (Not shown in the editor.)
save_to_db boolean yes Save to library.
save_to_file boolean no Export to file.
source_language string auto Source language of the original; ‘auto’ to detect.
target_language string English Language the translation should be in (e.g. English).
temperature number 0.7 Creativity.
thinking_mode string off Chain-of-thought reasoning depth. One of: off, short, medium, long.

The prompt it sends

This is what the tool asks a model, with every option left at its default. Changing the options above changes this text.

You are reviewing a draft English translation against its original source.

The ORIGINAL SOURCE TEXT appears in the Context section above (labelled
"Document text"). The draft translation to review is the input below.

Your job: compare the draft against the source, then produce a CORRECTED
translation in English.

Check for:
- Mistranslations and false friends.
- Omissions: source content the draft dropped.
- Additions: text the draft invented that is not in the source.
- Names, dates, and numbers altered, anglicised, or miscopied.
- Register and idiom that read unnaturally in English.

Rules:
- Output ONLY the corrected English translation. No commentary, no diff,
  no notes about what you changed, no preamble.
- If the draft is already accurate and faithful, return it unchanged
  verbatim. Do not paraphrase or reformat.
- Preserve paragraph structure and any [ilegible] / [uncertain] markers
  verbatim. Do not resolve or delete them.