Skip to main content
Back to challenges
Challenge

TypeScript Crude Export Workflow Streaming Dashboard with Vercel AI SDK

Port authority managers and trading executives require real-time streaming updates of crude export permit applications, vessel status, and operational alerts. Build a full-stack TypeScript streaming web application using Vercel AI SDK. The application leverages AI SDK's `streamText` and `useChat` hooks with structured JSON schema streaming (`streamObject`) to provide dynamic real-time status updates, bilingual contract summaries, and immediate compliance verification for oil shipments.

Business OperationsHosted 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 real-time streaming TypeScript operations dashboard for crude exports using Vercel AI SDK.

Delivery guide

How work is evaluated

Evaluation

Evaluates valid Zod object streaming and frontend payload serialization.

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

schema_validation_passed

Ensure output conforms to Zod permit schema.

Binary check

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

Dimension 2

time_to_first_token_ms

Latency to start streaming object tokens. • target: 250 • range: 0-1000

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 structured object streaming with Vercel AI SDK `streamObject`.

  • Build dynamic UI client components reacting to live streaming AI outputs.

  • Handle bilingual Arabic/English document summary streaming.

Resources and assets

Reference links and supporting material

Dataset notes

Export permit application data structures for TypeScript streaming validation.

Challenge setup

Evaluates valid Zod object streaming and frontend payload serialization.

Challenge input

JSON with application_id and vessel_name

AI SDK

Vercel's standard library for TypeScript AI streaming.

Evaluated output

JSON matching Zod permit validation schema

Evaluation checks
  • Ensure output conforms to Zod permit schema.
  • Latency to start streaming object tokens. • target: 250 • range: 0-1000
Configured evaluation evidence
  • Benchmark: Vercel-Streaming-Bench
  • Time To First Token Ms target: 250
  • 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
  • Hamming · Optional
  • Aim · Optional
Orchestration
  • Vercel AI SDK · Required

Evaluation contract

  • schema_validation_passed · Weight 1
  • time_to_first_token_ms · Weight 1

Metrics

  • time_to_first_token_ms · Target 250

Benchmarks

  • Vercel-Streaming-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with application_id and vessel_name

    Output: JSON matching Zod permit validation schema

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · Streaming Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about TypeScript Crude Export Workflow Streaming Dashboard with Vercel AI SDK