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.
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.
How work is evaluated
Evaluates type validity and exactness of GFA calculations based on URA plot ratios.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
gfa_math_check
Verifies max_gfa_sqm equals site_area_sqm multiplied by plot_ratio
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
schema_compliance
Percentage of generated responses matching Pydantic output model • target: 1 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
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.
Reference links and supporting material
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
- 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
- Benchmark: Pydantic-Eval-Bench
- Schema Compliance target: 1
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- Pydantic AI · Required
- AI21 Studio · Optional
- Ray Tune · Optional
- 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.