Skip to main content
Back to challenges
Challenge

Build a MAS CPI Inflation Risk Analyzer with Google ADK and OpenRouter

Develop an automated workflow to process Monetary Authority of Singapore CPI reports and detect retail price anomalies. Using Google ADK and OpenRouter, your agent will parse tabular CPI releases, calculate core inflation variances, and generate automated risk alerts with high precision.

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.

Implement a Google ADK agent routed through OpenRouter models to process MAS consumer price data and alert on core inflation deviations.

Delivery guide

How work is evaluated

Evaluation

Evaluate the agent's ability to accurately extract MAS CPI data and output formatted inflation alerts.

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

schema_conformance

Output matches required JSON structure with exact keys

Binary check

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

Dimension 2

extraction_accuracy

Accuracy of extracted numerical indicators • 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

  • Integrate Google ADK with OpenRouter model endpoints for financial text extraction

  • Build dynamic schema validation for MAS CPI tabular releases

  • Construct automated inflation variance calculation and alerting routines

  • Deploy audit-ready reporting pipelines for compliance verification

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic and actual MAS CPI press release documents paired with target JSON schemas.

Challenge setup

Evaluate the agent's ability to accurately extract MAS CPI data and output formatted inflation alerts.

Challenge input

JSON containing raw text of MAS CPI release

Google ADK

Agent development kit for Vertex AI integration.

OpenRouter

Provides multi-model fallbacks for domain parsing.

Evaluated output

JSON containing categorized core_cpi, headline_cpi, and flagged_anomalies array

Evaluation checks
  • Output matches required JSON structure with exact keys
  • Accuracy of extracted numerical indicators • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: MAS_FinText_Extract_v1
  • Extraction 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
  • Google ADK · Optional
  • Google · Optional
Policy Serving
  • OpenRouter · Required
Orchestration
  • OpenRouter · Required

Evaluation contract

  • schema_conformance · Weight 1
  • extraction_accuracy · Weight 1

Metrics

  • extraction_accuracy · Target 0.95

Benchmarks

  • MAS_FinText_Extract_v1
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing raw text of MAS CPI release

    Output: JSON containing categorized core_cpi, headline_cpi, and flagged_anomalies array

    Execution harness: Python

Evaluation tools

  • Google ADK · Agent Framework
  • OpenRouter · LLM Router

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a MAS CPI Inflation Risk Analyzer with Google ADK and OpenRouter