Skip to main content
Loading navigation
Back to challenges

Global Development Restart Pipeline using OpenAI Agents SDK on Vertex AI

Major global real estate developers like Hines are restarting development pipelines under shifting interest rates. Build an underwriting pipeline using the OpenAI Agents SDK hosted on Google Vertex AI to evaluate project restart triggers across commercial and multifamily properties with 95% metric precision.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Deploy an OpenAI Agents SDK workflow running on Google Vertex AI runtime that ingests macroeconomic yield spreads and local construction cost indices to recommend development restart timing.

How work is evaluated

Evaluation

Evaluates OpenAI Agents SDK decision logic regarding development project restart triggers.

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

Restart Recommendation Accuracy

Ensures 'GO' or 'HOLD' recommendation correctly aligns with financial threshold rules.

Binary check

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

Dimension 2

yield_on_cost_mae

Mean Absolute Error of calculated Yield on Cost metric • target: 0.001 • range: 0-0.05

Binary check

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

Learning goals

  • Utilize the OpenAI Agents SDK for creating multi-agent handoffs between market research and underwriting units.

  • Deploy inference calls via Google Vertex AI model endpoints.

  • Evaluate Yield-on-Cost (YoC) and capitalization rate spread thresholds.

  • Generate actionable development restart trigger signals.

Resources

Dataset notes

Dataset of 35 real estate development projects detailing estimated ground-up budget, projected NOI, exit capitalization rates, and financing interest rates.

Challenge setup

Evaluates OpenAI Agents SDK decision logic regarding development project restart triggers.

Challenge input

JSON containing projected_stabilized_noi, total_development_cost, exit_cap_rate, and debt_service_rate

OpenAI Agents SDK

Mandatory SDK for defining multi-agent workflows and handoffs.

Google Vertex AI

Required enterprise cloud runtime for hosting model endpoints.

Evaluated output

JSON with yield_on_cost, cap_rate_spread_bps, restart_recommendation ('GO'|'HOLD'), and target_quarter

Evaluation checks
  • Ensures 'GO' or 'HOLD' recommendation correctly aligns with financial threshold rules.
  • Mean Absolute Error of calculated Yield on Cost metric • target: 0.001 • range: 0-0.05
Configured evaluation evidence
  • Benchmark: CRE Investment Decision Benchmark
  • Yield On Cost Mae target: 0.001
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python 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
  • Exa · Required
  • OpenAI · Optional
  • Google Vertex AI · Optional

Evaluation contract

  • Restart Recommendation Accuracy · Weight 1
  • yield_on_cost_mae · Weight 1

Metrics

  • yield_on_cost_mae · Target 0.001

Benchmarks

  • CRE Investment Decision Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing projected_stabilized_noi, total_development_cost, exit_cap_rate, and debt_service_rate

    Output: JSON with yield_on_cost, cap_rate_spread_bps, restart_recommendation ('GO'|'HOLD'), and target_quarter

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Agent Framework
  • Google Vertex AI · Inference Infrastructure

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Global Development Restart Pipeline using OpenAI Agents SDK on Vertex AI