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.
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.
How work is evaluated
Evaluate the agent's ability to accurately extract MAS CPI data and output formatted inflation alerts.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
schema_conformance
Output matches required JSON structure with exact keys
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
extraction_accuracy
Accuracy of extracted numerical indicators • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
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
Reference links and supporting material
Synthetic and actual MAS CPI press release documents paired with target JSON schemas.
How this agent runs
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
- Output matches required JSON structure with exact keys
- Accuracy of extracted numerical indicators • target: 0.95 • range: 0-1
- Benchmark: MAS_FinText_Extract_v1
- Extraction Accuracy target: 0.95
- 1 public reference case
- Python execution harness
- Python sandbox
View technical recipe
Configured tools
- Google ADK · Optional
- Google · Optional
- OpenRouter · Required
- OpenRouter · Required
Evaluation contract
- schema_conformance · Weight 1
- extraction_accuracy · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.