Skip to main content
Back to challenges
Challenge

Build a Real-Time TypeScript Card Ledger Anomaly Engine with AI SDK

Legacy banking platforms undergoing modern cloud migration risk missing real-time transactional anomalies. Build a edge-ready TypeScript dynamic anomaly engine using Vercel AI SDK to stream, parse, and score incoming credit card ledger entries with sub-50ms execution speed.

CybersecurityHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Utilize Vercel AI SDK in TypeScript to build real-time streaming transaction anomaly scoring workflows on edge infrastructure.

Delivery guide

How work is evaluated

Evaluation

Evaluates streaming latency, schema compliance, and anomaly classification 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

stream_completion_test

Stream must successfully complete without runtime exception.

Binary check

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

Dimension 2

stream_latency_ms

Latency duration to first token response. • target: 45 • range: 0-100

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 real-time streaming LLM functions using Vercel AI SDK

  • Develop edge-compatible TypeScript validation pipelines for payment messages

  • Detect double-spending and out-of-sequence ledger anomalies in web applications

  • Achieve sub-50ms response streaming overhead for real-time risk decisions

Resources and assets

Reference links and supporting material

Dataset notes

Dataset of credit card ledger transaction streams with annotated sequence anomalies and double-spend attempts.

Challenge setup

Evaluates streaming latency, schema compliance, and anomaly classification precision.

Challenge input

JSON transaction stream event payload

AI SDK

Provides fast streaming AI capabilities optimized for web edge environments.

Evaluated output

JSON risk assessment output with stream duration metrics

Evaluation checks
  • Stream must successfully complete without runtime exception.
  • Latency duration to first token response. • target: 45 • range: 0-100
Configured evaluation evidence
  • Benchmark: TypeScript Stream Performance Suite
  • Stream Latency Ms target: 45
  • 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
Orchestration
  • Vercel AI SDK · Required

Evaluation contract

  • stream_completion_test · Weight 1
  • stream_latency_ms · Weight 1

Metrics

  • stream_latency_ms · Target 45

Benchmarks

  • TypeScript Stream Performance Suite
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON transaction stream event payload

    Output: JSON risk assessment output with stream duration metrics

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · TypeScript Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Real-Time TypeScript Card Ledger Anomaly Engine with AI SDK