Adam Fallon

LLM Translation: Building Real-Time Multilingual Features with Claude

  • LLM
  • Translation
  • Product Engineering

Introduction

Travel disruptions are already stressful. If the message is in the wrong language, it is worse. At Trainline we saw a clear gap: disruption messages were not translated for customers traveling internationally.

We asked a simple question: can LLMs close that gap quickly enough for real-time use?

LLM Translation: Building Real-Time Multilingual Features with Claude — image 1

Fixing this would improve customer retention and give us a reusable foundation for future multilingual features.

The Hypothesis

Our AI Lab strategy was to build small, useful services that could later plug into bigger systems. Real-time translation fit that model.

We hypothesized it would:

  • Differentiate Trainline from competitors like Omio and Uber
  • Reduce disruption-related frustration and improve retention
  • Create a translation capability we could reuse across products

We also wanted evidence that LLMs could handle low-resource translation. The paper From LLM to NMT: Advancing Low-Resource Machine Translation with Claude provided strong results for Claude 3.5.

LLM Translation: Building Real-Time Multilingual Features with Claude — image 2

The Approach

We focused on three areas:

  • Prompt design
    • Inject Trainline-specific vocabulary for context
    • Adjust to source and target languages dynamically

LLM Translation: Building Real-Time Multilingual Features with Claude — image 3

  • Technical implementation
    • Embed translations directly in disruption notifications
    • Keep the system language-agnostic for future expansion
  • Evaluation
    • Offline: BLEU scores for translation quality
    • Online: A/B tests for satisfaction and retention

LLM Translation: Building Real-Time Multilingual Features with Claude — image 4

LLM Translation: Building Real-Time Multilingual Features with Claude — image 5

What we built - A C# Library called Trainline.TranslationService

  • A database of Trainline-specific terms to inject into the prompt
  • A Python backend service that connects to AWS Bedrock (Claude 3.5)

LLM Translation: Building Real-Time Multilingual Features with Claude — image 6

LLM Translation: Building Real-Time Multilingual Features with Claude — image 7

LLM Translation: Building Real-Time Multilingual Features with Claude — image 8

Outcomes

  • Fewer complaints about unreadable disruption messages
  • More positive feedback on clarity during disruptions
  • A reusable translation service we can plug into new products

Learnings

Real-time translation is hard: accuracy, latency, and cost all matter. But careful prompt design plus strong LLMs made it viable. The bigger lesson was product focus: solving a real pain point creates momentum for future features.

LLM Translation: Building Real-Time Multilingual Features with Claude — image 9

Recap

By fixing untranslated disruption messages, we improved the immediate customer experience and built a foundation for future multilingual features. Real-time LLM translation is more than a nice-to-have; it is a step toward a global travel assistant.

If you’re interested in building production systems, check out my post on how I built this blog with Emacs and Docker.