Skip to main content
Loading navigation
Back to challenges

Singapore URA Tender Plot Ratio Analyzer using Vercel AI SDK

Singapore's Urban Redevelopment Authority (URA) frequently releases prime land sites like Marina Gardens Lane with strict plot ratio caps. Build a full-stack land tender bidding assistant using the Vercel AI SDK (TypeScript) that parses URA release notices and generates maximum allowable Gross Floor Area (GFA) proposals.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Develop an interactive TypeScript application with Vercel AI SDK streaming tools that extracts plot ratios and zoning restrictions from URA press releases to optimize tender land bids.

How work is evaluated

Evaluation

Evaluates URA site tender parsing and gross floor area calculation accuracy.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

GFA Calculation Exact Match

Verifies that max_gfa_sqm exactly equals site_area * gross_plot_ratio.

Binary check

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

Dimension 2

unit_yield_error

Absolute error in predicted residential unit yield • target: 0 • range: 0-10

Binary check

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

Learning goals

  • Build a streaming web interface using Vercel AI SDK `generateText` and `streamUI`.

  • Parse Singapore URA land sale parameters including site area and Gross Plot Ratio (GPR).

  • Calculate total maximum Gross Floor Area (GFA) and projected residential unit yield.

  • Format structured bid submission objects according to URA regulatory standards.

Resources

Dataset notes

Dataset of 25 Singapore URA land sale announcements, including site areas, gross plot ratios, land use zones, and winning bid histories.

Challenge setup

Evaluates URA site tender parsing and gross floor area calculation accuracy.

Challenge input

JSON containing site_location, site_area_sqm, gross_plot_ratio, and estimated_avg_unit_size_sqm

AI SDK

Mandatory Vercel framework for streaming AI applications.

Evaluated output

JSON with max_gfa_sqm, estimated_unit_yield, and tender_bid_ceiling_sgd

Evaluation checks
  • Verifies that max_gfa_sqm exactly equals site_area * gross_plot_ratio.
  • Absolute error in predicted residential unit yield • target: 0 • range: 0-10
Configured evaluation evidence
  • Benchmark: Urban Planning Technical Benchmark
  • Unit Yield Error target: 0
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • Vercel AI SDK · Required
  • Sacred · Optional
  • Synthflow · Optional
Orchestration
  • Vercel AI SDK · Required

Evaluation contract

  • GFA Calculation Exact Match · Weight 1
  • unit_yield_error · Weight 1

Metrics

  • unit_yield_error · Target 0

Benchmarks

  • Urban Planning Technical Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing site_location, site_area_sqm, gross_plot_ratio, and estimated_avg_unit_size_sqm

    Output: JSON with max_gfa_sqm, estimated_unit_yield, and tender_bid_ceiling_sgd

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · TypeScript Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Singapore URA Tender Plot Ratio Analyzer using Vercel AI SDK