Skip to main content
Back to challenges
Challenge

Long-Horizon Land Parcel Assembly Agent using OpenAI Agents SDK

Long-term institutional investors evaluate complex suburban land assembly opportunities with fragmented ownership. Build an autonomous agent using the OpenAI Agents SDK to parse property tax records, evaluate zoning aggregation rules, and model long-horizon IRR without execution errors.

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 an autonomous multi-turn land aggregation agent using the OpenAI Agents SDK and function-calling workflows.

Delivery guide

How work is evaluated

Evaluation

Evaluates land parcel aggregation suitability and long-horizon IRR calculations.

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

total_cost_math

Total acquisition cost equals total_acreage * average_cost_per_acre

Binary check

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

Dimension 2

irr_calculation_accuracy

Precision of 10-year calculated internal rate of return against financial formula • 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

  • Build an autonomous agent with the OpenAI Agents SDK using function calling and auto-tool execution.

  • Analyze tax map spatial layouts to identify adjacent sub-parcels suitable for assembly.

  • Calculate assembled land acquisition cost and project 10-year holding IRR.

  • Ensure robust agent tool response handling across multi-turn user sessions.

Resources and assets

Reference links and supporting material

Dataset notes

Suburban parcel boundary maps, tax assessment records, and zoning aggregation regulations.

Challenge setup

Evaluates land parcel aggregation suitability and long-horizon IRR calculations.

Challenge input

JSON containing parcel_ids array, total_acreage, average_cost_per_acre, projected_exit_psf

OpenAI Agents SDK

Framework assignment for building OpenAI autonomous function agents.

Evaluated output

JSON with assembly_viable boolean, total_acquisition_cost, projected_10yr_irr

Evaluation checks
  • Total acquisition cost equals total_acreage * average_cost_per_acre
  • Precision of 10-year calculated internal rate of return against financial formula • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: OpenAI-Agent-Bench
  • Irr Calculation Accuracy target: 0.95
  • 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
  • Ray Tune · Optional
  • LiveKit · Optional

Evaluation contract

  • total_cost_math · Weight 1
  • irr_calculation_accuracy · Weight 1

Metrics

  • irr_calculation_accuracy · Target 0.95

Benchmarks

  • OpenAI-Agent-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing parcel_ids array, total_acreage, average_cost_per_acre, projected_exit_psf

    Output: JSON with assembly_viable boolean, total_acquisition_cost, projected_10yr_irr

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Autonomous Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Long-Horizon Land Parcel Assembly Agent using OpenAI Agents SDK