Back to challenges
Challenge

LEI Governance Graph Agent with LangChain & LangGraph

Unowned and stale Legal Entity Identifier (LEI) records create critical blind spots in financial counterparty identification and trade reporting. Build an LEI portfolio governance agent using LangChain and LangGraph to track entity ownership changes, evaluate registration drift, and flag orphan records with 95% accuracy across global LEI datasets.

CybersecurityHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build a stateful, graph-based governance tracking workflow using LangChain and LangGraph to detect orphaned and stale LEI portfolios.

Delivery guide

How work is evaluated

Evaluation

Evaluates orphan LEI identification accuracy and correctness of state graph transitions.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

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

graph_execution_success

Verifies that the LangGraph workflow completed without state execution errors.

Binary check

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

Dimension 2

orphan_detection_accuracy

Accuracy of identifying unowned and lapsed LEI records. • target: 0.95 • 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

  • Design stateful LangGraph node workflows representing entity lifecycle stages

  • Construct LangChain tool interfaces to query GLEIF open APIs and registry databases

  • Detect unassigned, expired, or orphaned LEI records across institutional portfolios

  • Generate automated compliance remediation tickets for institutional ops teams

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic portfolio of 500 LEI records representing diverse status types (ISSUED, LAPSED, MERGED, RETIRED) across global asset managers.

How this agent runs

Evaluates orphan LEI identification accuracy and correctness of state graph transitions.

Challenge input

JSON array of corporate LEI records containing registration status and renewal date

LangChain

Framework for building chains and tool integration.

LangGraph

Stateful workflow orchestration engine for complex decision graphs.

Evaluated output

JSON governance status report detailing orphan_count, lapsed_count, and actions_required

Checks for
  • Verifies that the LangGraph workflow completed without state execution errors.
  • Accuracy of identifying unowned and lapsed LEI records. • target: 0.95 • range: 0-1
Proof of success
  • Benchmark: LEIGovernance-Bench-v1
  • Orphan Detection Accuracy target: 0.95
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

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

Evaluation contract

  • graph_execution_success · Weight 1
  • orphan_detection_accuracy · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about LEI Governance Graph Agent with LangChain & LangGraph