Skip to main content
Back to challenges
Challenge

Crypto Banking Access Risk Firewall with Vercel AI SDK

Financial institutions onboarding crypto asset service providers require continuous monitoring of fiat-to-crypto gateway flows and counterparty risk scores. You will create a real-time risk evaluation service that streams risk telemetry and automatically throttles high-risk settlements under configurable compliance policies.

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.

Build a streaming crypto-fiat banking gateway risk firewall in Next.js using the Vercel AI SDK to monitor counterparty transactions in real time.

Delivery guide

How work is evaluated

Evaluation

Evaluates streaming decision latency and risk decision precision for fiat-crypto settlement requests.

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

triggers_circuit_breaker

Ensures high volume transfer to high risk jurisdiction is THROTTLED or BLOCKED

Binary check

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

Dimension 2

stream_first_chunk_latency_ms

Latency to first streamed response byte • target: 80 • range: 0-300

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 tools using Vercel AI SDK (`ai`)

  • Create continuous counterparty risk scoring models for fiat-crypto gateways

  • Enforce dynamic credit limits based on real-time transaction velocity

  • Stream risk evaluations directly to web dashboard clients with low latency

Resources and assets

Reference links and supporting material

Dataset notes

Stream of 1,000 crypto asset service provider (CASP) wire transfer events with varying volume spikes and risk indicators.

Challenge setup

Evaluates streaming decision latency and risk decision precision for fiat-crypto settlement requests.

Challenge input

JSON containing transfer_id, casp_id, volume, and recipient

AI SDK

Vercel AI SDK for building streaming AI web infrastructure in TypeScript.

Evaluated output

Streamed JSON chunks culminating in action ('ALLOW'|'THROTTLE'|'BLOCK')

Evaluation checks
  • Ensures high volume transfer to high risk jurisdiction is THROTTLED or BLOCKED
  • Latency to first streamed response byte • target: 80 • range: 0-300
Configured evaluation evidence
  • Benchmark: StreamRisk-Bench
  • Stream First Chunk Latency Ms target: 80
  • 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

  • triggers_circuit_breaker · Weight 1
  • stream_first_chunk_latency_ms · Weight 1

Metrics

  • stream_first_chunk_latency_ms · Target 80

Benchmarks

  • StreamRisk-Bench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing transfer_id, casp_id, volume, and recipient

    Output: Streamed JSON chunks culminating in action ('ALLOW'|'THROTTLE'|'BLOCK')

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · agent_framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Crypto Banking Access Risk Firewall with Vercel AI SDK