Skip to main content
Back to challenges
Challenge

OpenAI Agents SDK Consumer Inflation Analysis Agent

Develop an autonomous OpenAI Agents SDK agent using multi-turn function calling to ingest CPI raw time-series data and generate macro-economic policy recommendations for MAS regulators. Deliver precise metric calculations with 95% evaluation accuracy.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Build an autonomous analytical agent with OpenAI Agents SDK to parse Singapore CPI releases and simulate monetary policy decisions.

Delivery guide

How work is evaluated

Evaluation

Evaluates calculation accuracy for MAS Core Inflation and evaluation logic against ground truth economic figures.

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

Math Precision Test

Checks if core inflation YoY calculation matches exact mathematical expectation

Binary check

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

Dimension 2

economic_analysis_accuracy

Accuracy of policy recommendation logic • 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

  • Utilize OpenAI Agents SDK for autonomous function calling and loop execution

  • Ingest Consumer Price Index (CPI) and MAS Core Inflation monthly statistical releases

  • Build tool integrations for time-series trend extrapolation and basket variance analysis

  • Generate executive briefings on monetary policy stance options

Resources and assets

Reference links and supporting material

Dataset notes

Historical and synthetic Singapore Consumer Price Index (CPI) basket time-series data.

Challenge setup

Evaluates calculation accuracy for MAS Core Inflation and evaluation logic against ground truth economic figures.

Challenge input

JSON containing CPI index values for current month and previous year

OpenAI Agents SDK

OpenAI's official Python framework for function-calling agents

Evaluated output

JSON containing headline_cpi_yoy, mas_core_yoy, and recommendation

Evaluation checks
  • Checks if core inflation YoY calculation matches exact mathematical expectation
  • Accuracy of policy recommendation logic • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: EconBench
  • Economic Analysis 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
  • Lindy · Optional
  • Langroid · Optional

Evaluation contract

  • Math Precision Test · Weight 1
  • economic_analysis_accuracy · Weight 1

Metrics

  • economic_analysis_accuracy · Target 0.95

Benchmarks

  • EconBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing CPI index values for current month and previous year

    Output: JSON containing headline_cpi_yoy, mas_core_yoy, and recommendation

    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 Consumer Inflation Analysis Agent