Skip to main content
Back to challenges
Challenge

NYC Rental Fee Compliance Assistant with Vercel AI SDK and Synthflow

NYC's FARE Act prohibits brokers from passing fee burdens onto tenants, disrupting traditional rental listings. Construct an interactive voice and text compliance bot using Vercel AI SDK and Synthflow to review lease agreements and listing syndication outputs. Ensure 95% detection of illegal fee structures across tenant applications.

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 a compliance agent using Vercel AI SDK integrated with Synthflow to detect illegal fee shifting under NYC rental regulations.

Delivery guide

How work is evaluated

Evaluation

Evaluates detection precision of non-compliant tenant broker fee clauses in listing contracts.

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

flag_accuracy

Verifies correct identification of illegal fee status.

Binary check

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

Dimension 2

clause_precision

Precision score of extracted non-compliant text snippets. • target: 0.95 • 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

  • Integrate Vercel AI SDK streaming tools with TypeScript backend endpoints

  • Connect Synthflow interface endpoints for interactive compliance screening

  • Parse NYC rental listing contracts to flag FARE Act violations

  • Generate compliance scorecard reports for property management agents

Resources and assets

Reference links and supporting material

Dataset notes

Collection of NYC rental listings, lease agreements, and fee terms labeled for FARE Act compliance.

Challenge setup

Evaluates detection precision of non-compliant tenant broker fee clauses in listing contracts.

Challenge input

JSON object with contract_text and listing_agent_id

AI SDK

Vercel AI SDK for TypeScript interface execution.

Synthflow

Required assistant integration tool.

Evaluated output

JSON object with holds_illegal_fee (boolean), flagged_clauses (array of strings)

Evaluation checks
  • Verifies correct identification of illegal fee status.
  • Precision score of extracted non-compliant text snippets. • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: LegalComplianceBench
  • Clause Precision 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

Action Space
  • Synthflow · Required
  • Vercel AI SDK · Optional
  • Kore.ai · Optional
Orchestration
  • Vercel AI SDK · Optional

Evaluation contract

  • flag_accuracy · Weight 1
  • clause_precision · Weight 1

Metrics

  • clause_precision · Target 0.95

Benchmarks

  • LegalComplianceBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with contract_text and listing_agent_id

    Output: JSON object with holds_illegal_fee (boolean), flagged_clauses (array of strings)

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · Agent Core Framework
  • Synthflow · Assistant Voice/Web UI

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about NYC Rental Fee Compliance Assistant with Vercel AI SDK and Synthflow