UPI Fraud Risk Triage Engine with Pydantic AI & Claude 4.1 Opus
Retail investment and fintech payment networks require sub-second fraud detection across high-volume UPI transactions. Build a real-time merchant risk engine using Pydantic AI and Claude 4.1 Opus to evaluate transaction metadata and flag synthetic fraud with 98% precision.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop a type-safe UPI transaction fraud evaluation agent using Pydantic AI and Claude 4.1 Opus with Pydantic schema validation.
How work is evaluated
Evaluates accuracy of UPI fraud flagging and false positive rates under production load constraints.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
pydantic_schema_strictness
Validates that all agent outputs comply exactly with output Pydantic model
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
fraud_detection_precision
Precision of blocked transactions matching gold label fraud cases • target: 0.98 • 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
Master type-safe agent development using Pydantic AI dependencies and result validation
Leverage Claude 4.1 Opus for complex financial anomaly reasoning
Integrate device risk signals and merchant velocity metrics
Enforce strict SLA bounds (< 150ms reasoning overhead) via stream parsing
Reference links and supporting material
UPI transaction telemetry stream with simulated mule VPAs, device hopping patterns, and merchant velocity metrics.
Challenge setup
Evaluates accuracy of UPI fraud flagging and false positive rates under production load constraints.
Challenge input
JSON transaction metadata with device ID, amount, and vpa_history
Pydantic AI
Type-safe agent framework for Python built on Pydantic.
Claude 4.1 Opus
High-reasoning LLM for complex anomaly and risk evaluation.
Evaluated output
JSON containing risk_score, action (ALLOW|BLOCK|FLAG), and reason
- Validates that all agent outputs comply exactly with output Pydantic model
- Precision of blocked transactions matching gold label fraud cases • target: 0.98 • range: 0-1
- Benchmark: UPI Financial Fraud Triage Benchmark
- Fraud Detection Precision target: 0.98
- 1 public reference case
- 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
- Pydantic AI · Required
- BoTorch · Optional
- Claude 4.1 Opus · Optional
- Pydantic AI · Required
Evaluation contract
- pydantic_schema_strictness · Weight 1
- fraud_detection_precision · Weight 1
Metrics
- fraud_detection_precision · Target 0.98
Benchmarks
- UPI Financial Fraud Triage Benchmark
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON transaction metadata with device ID, amount, and vpa_history
Output: JSON containing risk_score, action (ALLOW|BLOCK|FLAG), and reason
Execution harness: Python
Evaluation tools
- Pydantic AI · Agent Orchestration Framework
- Claude 4.1 Opus · Models
Recipe freeze marker
No recipe freeze time is recorded.