Skip to main content
Back to challenges
Challenge

NYC Rental Regulatory Compliance Auditor with Vercel AI SDK & Bolt.new

NYC's FARE Act banning tenant-paid broker fees has led to convoluted leasing fee workarounds. Build a web-accessible compliance scanner using Vercel AI SDK and Bolt.new to automatically analyze apartment listing descriptions and fee disclosures for illegal disguised tenant charges. Identify non-compliant lease clauses with 90%+ recall.

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.

Develop an automated leasing compliance scanner using Vercel AI SDK tools and Bolt.new rapid deployment to detect hidden tenant fees.

Delivery guide

How work is evaluated

Evaluation

Evaluates legal compliance classification accuracy on residential lease listing disclosures.

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

Violation Flagging Test

Correctly flags non-compliant key fee

Binary check

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

Dimension 2

Classification Accuracy

Accuracy across benchmark listing samples • target: 0.95 • range: 0.8-1

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 classification with Vercel AI SDK

  • Build rapid prototype interface using Bolt.new AI scaffolding

  • Identify prohibited broker fee disguises such as 'administrative access fees'

  • Generate official violation reports formatted for local housing authorities

Resources and assets

Reference links and supporting material

Dataset notes

Rental listing descriptions and lease fee disclosure terms gathered post-FARE Act implementation.

Challenge setup

Evaluates legal compliance classification accuracy on residential lease listing disclosures.

Challenge input

JSON with listing_description, fee_breakdown

AI SDK

Provides structured streaming and tool integration

Bolt.new

Enables rapid full-stack application prototyping

Evaluated output

JSON with is_compliant (boolean), detected_violations (array)

Evaluation checks
  • Correctly flags non-compliant key fee
  • Accuracy across benchmark listing samples • target: 0.95 • range: 0.8-1
Configured evaluation evidence
  • Benchmark: LegalComplianceBench
  • Classification Accuracy target: 0.95
  • 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

Environment
  • Bolt.new · Required
Action Space
  • Bolt.new · Required
  • Vercel AI SDK · Optional
  • Arize AI · Optional
Orchestration
  • Vercel AI SDK · Optional

Evaluation contract

  • Violation Flagging Test · Weight 1
  • Classification Accuracy · Weight 1

Metrics

  • Classification Accuracy · Target 0.95

Benchmarks

  • LegalComplianceBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with listing_description, fee_breakdown

    Output: JSON with is_compliant (boolean), detected_violations (array)

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · TypeScript AI SDK
  • Bolt.new · Development Environment

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about NYC Rental Regulatory Compliance Auditor with Vercel AI SDK & Bolt.new