Skip to main content
Back to challenges
Challenge

VASP On-Chain Compliance Monitoring Pipeline with Pydantic AI

Construct a type-safe compliance monitoring agent using Pydantic AI to validate Virtual Asset Service Provider (VASP) transactions. Enforce Singapore Monetary Authority requirements for travel rule data transmission and sanctioned wallet identification.

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.

Develop a strongly typed Pydantic AI agent workflow to audit crypto transactions against MAS VASP regulatory expectations.

Delivery guide

How work is evaluated

Evaluation

Evaluates Travel Rule flag enforcement and sanction list matching correctness.

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

pydantic_schema_valid

Ensures agent output strictly parses into Pydantic model without validation errors

Binary check

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

Dimension 2

rule_accuracy

Accuracy of Travel Rule triggering based on SGD threshold • target: 1 • 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

  • Build type-safe agent state and output models using Pydantic AI and Pydantic v2

  • Implement custom dependency injection for live blockchain RPC and OFAC sanction list providers

  • Enforce Travel Rule compliance thresholds ($1,000 SGD equivalent) automatically

  • Construct deterministic compliance loggers emit cryptographic audit trails

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic dataset of 40 crypto asset transfer records with metadata.

Challenge setup

Evaluates Travel Rule flag enforcement and sanction list matching correctness.

Challenge input

JSON containing transfer_details and entity_info

Pydantic AI

Guarantees output structures and type validation using Pydantic v2.

Evaluated output

JSON conforming to VaspComplianceResult Pydantic schema

Evaluation checks
  • Ensures agent output strictly parses into Pydantic model without validation errors
  • Accuracy of Travel Rule triggering based on SGD threshold • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Crypto Compliance Eval Suite
  • Rule Accuracy target: 1
  • 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
  • Pydantic AI · Required
  • Martian · Optional
  • Deepgram · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • pydantic_schema_valid · Weight 1
  • rule_accuracy · Weight 1

Metrics

  • rule_accuracy · Target 1

Benchmarks

  • Crypto Compliance Eval Suite
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing transfer_details and entity_info

    Output: JSON conforming to VaspComplianceResult Pydantic schema

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Type-Safe Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about VASP On-Chain Compliance Monitoring Pipeline with Pydantic AI