Skip to main content
Loading navigation
Back to challenges

Stateful VASP Travel Rule Compliance Pipeline with LangChain & LangGraph

Virtual Asset Service Providers must perform strict cross-border identity checks under MAS regulatory guidelines. Construct a stateful graph workflow using LangChain and LangGraph to perform identity resolution and execute travel rule data exchanges.

Workflow AutomationHosted by Vera
Sign in free to start

What you are building

Develop a stateful VASP Travel Rule transaction compliance pipeline using LangChain and LangGraph state machines.

How work is evaluated

Evaluation

Evaluates state transitions, sanction checks, and Travel Rule payload completeness.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

check_travel_rule_flag

Checks if threshold triggers travel rule

Binary check

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

Dimension 2

compliance_accuracy

Accuracy of regulatory decision state • 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

  • Construct stateful node graphs using LangGraph

  • Implement identity matching and sanctions screening logic

  • Manage human-in-the-loop validation triggers for non-standard transactions

Resources

Dataset notes

Synthetic virtual asset transfer requests with various customer identity attributes.

Challenge setup

Evaluates state transitions, sanction checks, and Travel Rule payload completeness.

Challenge input

JSON transaction with sender/receiver details and transfer amount

LangChain

Chain and integration support

LangGraph

Graph-based state machine and checkpoints

Evaluated output

JSON with status (APPROVED/HOLD/REJECTED) and travel_rule_required flag

Evaluation checks
  • Checks if threshold triggers travel rule
  • Accuracy of regulatory decision state • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: VASP-Bench
  • Compliance Accuracy target: 1
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • LangChain · Required
  • Langchain · Optional
  • Twin · Optional
Orchestration
  • LangChain · Required
  • Langchain · Optional

Evaluation contract

  • check_travel_rule_flag · Weight 1
  • compliance_accuracy · Weight 1

Metrics

  • compliance_accuracy · Target 1

Benchmarks

  • VASP-Bench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON transaction with sender/receiver details and transfer amount

    Output: JSON with status (APPROVED/HOLD/REJECTED) and travel_rule_required flag

    Execution harness: Python

Evaluation tools

  • LangChain · LLM Orchestration Framework
  • LangGraph · Stateful Agent Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Stateful VASP Travel Rule Compliance Pipeline with LangChain & LangGraph