Scalable UPI Merchant Fraud Triage Agent using Google ADK and Galileo
With UPI transactions hitting 23.7 billion monthly, the volume of potential merchant-side fraud has scaled exponentially. This challenge requires building an automated fraud triage agent that processes high-velocity transaction logs and merchant metadata to identify high-risk patterns. You will leverage the Google Agent Development Kit (ADK) to build a multimodal agent that uses Gemini 1.5 Pro to analyze both structured transaction data and unstructured merchant verification documents (KYC images, storefront photos). The agent must utilize Galileo's monitoring suite to implement real-time guardrails, ensuring that automated fraud flags meet high precision standards before triggering account freezes. Your solution will need to handle India-specific context, such as diverse merchant categories and regional transaction behaviors, while maintaining the performance required for national-scale Digital Public Infrastructure.
What you are building
The core problem, expected build, and operating context for this challenge.
With UPI transactions hitting 23.7 billion monthly, the volume of potential merchant-side fraud has scaled exponentially. This challenge requires building an automated fraud triage agent that processes high-velocity transaction logs and merchant metadata to identify high-risk patterns. You will leverage the Google Agent Development Kit (ADK) to build a multimodal agent that uses Gemini 1.5 Pro to analyze both structured transaction data and unstructured merchant verification documents (KYC images, storefront photos). The agent must utilize Galileo's monitoring suite to implement real-time guardrails, ensuring that automated fraud flags meet high precision standards before triggering account freezes. Your solution will need to handle India-specific context, such as diverse merchant categories and regional transaction behaviors, while maintaining the performance required for national-scale Digital Public Infrastructure.
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.
High Risk Flagging
Must flag accounts with >100% volume increase in 1 hour as high risk.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Precision
Percentage of correctly identified fraud cases. • target: 0.9 • 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
Orchestrate multimodal agents using Google ADK to process both transaction CSVs and merchant storefront images
Implement RAG (Retrieval-Augmented Generation) on NPCI (National Payments Corporation of India) compliance guidelines using Vertex AI
Build a real-time monitoring dashboard using Galileo to track agent hallucinations and precision in fraud flagging
Design a custom reasoning loop in Google ADK that handles merchant disputes by summarizing historical transaction anomalies
Optimize Gemini prompt templates for low-latency fraud classification in high-throughput environments
Deploy the agent as a cloud function that triggers on UPI transaction webhooks for immediate risk scoring
How this agent runs
The system is evaluated based on its ability to correctly identify fraud in a synthetic UPI dataset and the latency of its multimodal analysis.
Challenge input
JSON containing merchant_id, transaction_history (list), and kyc_image_url
Google ADK
Required for building the multimodal agent logic.
Galileo
Ensures reliability and guardrails for automated risk decisions.
Gemini 1.5 Pro
Used for its large context window and multimodal capabilities.
Evaluated output
JSON containing risk_score (0-1), reasoning_string, and recommended_action
- Must flag accounts with >100% volume increase in 1 hour as high risk.
- Percentage of correctly identified fraud cases. • target: 0.9 • range: 0-1
- Benchmark: FraudDetection-v1
- Precision target: 0.9
- 1 public reference case
- Python execution harness
- Python sandbox
View technical recipe
Configured tools
- Google · Optional
- Google ADK · Optional
- Galileo · Required
- Galileo · Required
Evaluation contract
- High Risk Flagging · Weight 1
- Precision · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset
Versalist can run this agent on your behalf with your data. Tell us about your dataset and the result you need.
Discuss your dataset[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.