Skip to main content
Back to challenges
Challenge

OpenAI Agents SDK Suburban Land Assembly Feasibility Agent

Faith-based capital and institutional funds are targeting suburban land parcels for multi-decade land assembly plays. Build an autonomous land assembly agent using OpenAI Agents SDK to analyze adjacent suburban land parcels, estimate hold yields, and evaluate zoning change risks.

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.

Construct an autonomous suburban land assembly agent using OpenAI Agents SDK to model long-horizon land acquisition strategies.

Delivery guide

How work is evaluated

Evaluation

Evaluates accuracy of land assembly contiguity analysis and long-term hold ROI.

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

contiguity_sum_check

Checks that aggregated acreage matches sum of individual parcel areas.

Binary check

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

Dimension 2

assembly_cost_accuracy

Accuracy of total acquisition cost calculations across all parcels. • target: 0.98 • 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 OpenAI Agents SDK runner with function-calling tools

  • Build parcel aggregation algorithms that compute continuous parcel boundaries

  • Model 20-30 year long-horizon land holding costs and tax abatement potentials

  • Generate automated zoning risk profiles for multi-parcel suburban assemblies

Resources and assets

Reference links and supporting material

Dataset notes

Parcel boundary and tax assessment tabular data for 30 suburban land assembly opportunities.

Challenge setup

Evaluates accuracy of land assembly contiguity analysis and long-term hold ROI.

Challenge input

JSON containing parcel list with parcel_id, acreage, tax_assessed_value, contiguity_ids

OpenAI Agents SDK

Provides official OpenAI agent tool declarations and handoff orchestration.

Evaluated output

JSON with combined_acreage, total_acquisition_cost, assembly_viable boolean

Evaluation checks
  • Checks that aggregated acreage matches sum of individual parcel areas.
  • Accuracy of total acquisition cost calculations across all parcels. • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: SuburbanLandAssemblyBench
  • Assembly Cost Accuracy target: 0.98
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python 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
  • OpenAI · Required
  • LiveKit · Optional
  • NNI (Neural Network Intelligence) · Optional

Evaluation contract

  • contiguity_sum_check · Weight 1
  • assembly_cost_accuracy · Weight 1

Metrics

  • assembly_cost_accuracy · Target 0.98

Benchmarks

  • SuburbanLandAssemblyBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing parcel list with parcel_id, acreage, tax_assessed_value, contiguity_ids

    Output: JSON with combined_acreage, total_acquisition_cost, assembly_viable boolean

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about OpenAI Agents SDK Suburban Land Assembly Feasibility Agent