Skip to main content
Back to challenges
Challenge

Build a Cross-Border Trade Policy Translation Pipeline with Vercel AI SDK

Construct a streaming multi-lingual trade documentation translator and policy verifier for ASEAN-China trade agreements. Utilizing Vercel AI SDK in TypeScript, your workflow will stream translated customs declarations and verify trade code classifications in real time.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build a streaming TypeScript workflow using Vercel AI SDK to translate cross-border trade documents and validate HS code mappings.

Delivery guide

How work is evaluated

Evaluation

Evaluate translated customs metadata and HS code precision.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

hs_code_format

HS code is valid 6-digit numerical string

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

translation_bleu_score

BLEU translation quality score • target: 0.85 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Implement streaming text translation and structured object generation using Vercel AI SDK

  • Integrate `generateObject` with Zod schemas for trade HS code extraction

  • Design zero-latency streaming UI components for web customs portals

  • Validate translated trade descriptions against ASEAN customs registries

Resources and assets

Reference links and supporting material

Dataset notes

Bilingual trade manifest samples with standardized Harmonized System (HS) code mappings.

Challenge setup

Evaluate translated customs metadata and HS code precision.

Challenge input

JSON containing foreign_description and target_lang

AI SDK

Vercel toolkit for streaming and object generation.

Evaluated output

JSON with translated_text, hs_code, confidence

Evaluation checks
  • HS code is valid 6-digit numerical string
  • BLEU translation quality score • target: 0.85 • range: 0-1
Configured evaluation evidence
  • Benchmark: Trade_Translation_Bench
  • Translation Bleu Score target: 0.85
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Vercel AI SDK · Required
  • Pydantic AI · Optional
  • Ludwig · Optional
Orchestration
  • Vercel AI SDK · Required
  • Pydantic AI · Optional

Evaluation contract

  • hs_code_format · Weight 1
  • translation_bleu_score · Weight 1

Metrics

  • translation_bleu_score · Target 0.85

Benchmarks

  • Trade_Translation_Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing foreign_description and target_lang

    Output: JSON with translated_text, hs_code, confidence

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · TypeScript AI Library

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Cross-Border Trade Policy Translation Pipeline with Vercel AI SDK