Documents / Document Intelligence Live

Document Translation

Translate a document section by section, carrying terminology forward so the whole reads as one piece rather than a set of fragments.

  • Run on demand
  • ~8 credits per run
  • v1.0.0

What does Document Translation do?

Document Translation is a production AI agent in the documents section of the Leverge agent store, built for the document intelligence process. Translate a document section by section, carrying terminology forward so the whole reads as one piece rather than a set of fragments. It runs on demand, works through 6 steps and returns 4 outputs, including document details.

What it needs

  • Document to translate

    File upload

    pdf docx txt md

  • Translation settings

    Form

What it does

  1. Extracting text
  2. Building a terminology glossary
  3. Splitting into sections
  4. Translating section {{loop.index}} of {{loop.total}}
  5. Assembling the translation
  6. Preparing the side-by-side view

What you get back

  • Document details Metadata grid
  • Source and translation Side by side
  • Translation Markdown doc
  • Terminology glossary Markdown doc

After each run it asks: “Does this translation read well?” Answers feed the evaluation set, so the agent is measured against your own judgement rather than ours.

When it runs

Run on demand

Oversight

Runs under scoped, least-privilege credentials with every action written to an audit log. Anything that moves money, alters a contract or reaches a customer requires human approval before it executes.

Document Intelligence

Other agents in document intelligence

Extraction and classification across real-world file formats

  • Document Intelligence Live

    Document Comparison

    Compare two versions of a document side by side and list every substantive change, separating what alters meaning from what only alters wording.

  • Document Intelligence Live

    Document Summarization

    Upload a document and get a structured summary with key metadata and topics. Long documents are summarized section by section with rolling context.

  • Data Extraction Live

    OCR Data Extractor

    Read a scanned invoice or receipt and pull out the header fields and line items as structured data.

Next Step

Deploy Document Translation, or adapt it

It runs as-is against the inputs above. Most deployments diverge — a different source system, a different tolerance, a different approval path. A 30-minute technical call establishes which.

Book a Technical Call
  • No sales script
  • NDA on request
  • Scoping notes sent within 48 hours
Call us Book a call