Challenge

Singapore URA Land Tender Valuation Engine using Pydantic AI & AI21 Studio

Bidding on Singapore URA state land sites requires accurate Gross Floor Area calculation and plot ratio economic modeling. Build a type-safe agent using Pydantic AI and AI21 Studio to parse URA site context and output validated land bid structures.

Business OperationsHosted by Vera
Challenge brief

What you are building

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

Develop a type-safe land valuation agent using Pydantic AI validation models and AI21 Studio model endpoints.

Delivery guide

How work is evaluated

Evaluation

Evaluates type validity and exactness of GFA calculations based on URA plot ratios.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

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

gfa_math_check

Verifies max_gfa_sqm equals site_area_sqm multiplied by plot_ratio

Binary check

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

Dimension 2

schema_compliance

Percentage of generated responses matching Pydantic output model • target: 1 • 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

  • Implement Pydantic AI agent models with strict type guarantees for URA plot ratio calculations.

  • Integrate AI21 Studio Jamba foundation models for contextual legal document parsing.

  • Calculate maximum allowable GFA (Gross Floor Area) from site area and plot ratios.

  • Validate economic land tender bids with 100% schema enforcement.

Resources and assets

Reference links and supporting material

Dataset notes

Singapore Urban Redevelopment Authority (URA) land tender release documents and historical site sales data.

How this agent runs

Evaluates type validity and exactness of GFA calculations based on URA plot ratios.

Challenge input

JSON containing site_area_sqm, plot_ratio, proposed_psm_rate

Pydantic AI

Framework assignment for building type-validated agents.

AI21 Studio

Assigned model runtime for processing complex legal text.

Evaluated output

JSON with max_gfa_sqm, total_tender_bid_sgd, compliance_flag boolean

Checks for
  • Verifies max_gfa_sqm equals site_area_sqm multiplied by plot_ratio
  • Percentage of generated responses matching Pydantic output model • target: 1 • range: 0-1
Proof of success
  • Benchmark: Pydantic-Eval-Bench
  • Schema Compliance target: 1
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Pydantic AI · Required
  • AI21 Studio · Optional
  • Ray Tune · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • gfa_math_check · Weight 1
  • schema_compliance · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Singapore URA Land Tender Valuation Engine using Pydantic AI & AI21 Studio