Skip to main content
Back to challenges
Challenge

LangChain & All Hands AI Asset Management Compliance Suite

Construct a LangGraph and LangChain agentic workflow backed by All Hands AI developer tools to automatically review fund prospectus filings against MAS regulatory updates. Maintain 95% compliance accuracy across complex multi-page asset structures.

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 stateful LangGraph compliance engine aided by All Hands AI workspace tools to audit fund prospectus filings for MAS requirements.

Delivery guide

How work is evaluated

Evaluation

Evaluates compliance issue classification and graph state transition correctness on financial prospectuses.

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

Complete Audit Traversal

Ensures the state machine visited all required compliance nodes

Binary check

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

Dimension 2

audit_accuracy

Accuracy of flagged regulatory omissions • 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 complex state machines using LangChain's LangGraph framework

  • Integrate All Hands AI developer agent tools for autonomous debugging and code execution

  • Build compliance extraction pipelines tailored to Monetary Authority of Singapore fund rules

  • Implement multi-turn state persistence and checkpointing

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic dataset of Variable Capital Company (VCC) fund prospectuses and regulatory compliance checklists.

Challenge setup

Evaluates compliance issue classification and graph state transition correctness on financial prospectuses.

Challenge input

JSON containing prospectus clauses and fund parameters

LangChain

LangGraph state machine management for regulatory reviews

All Hands AI

Developer assistant tools for autonomous debugging

Evaluated output

JSON containing list of compliance gaps, status, and state graph nodes visited

Evaluation checks
  • Ensures the state machine visited all required compliance nodes
  • Accuracy of flagged regulatory omissions • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: FinEval
  • Audit Accuracy target: 0.95
  • 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
  • Langchain · Required
  • LangChain · Optional
  • All Hands AI · Optional
Orchestration
  • Langchain · Required
  • LangChain · Optional

Evaluation contract

  • Complete Audit Traversal · Weight 1
  • audit_accuracy · Weight 1

Metrics

  • audit_accuracy · Target 0.95

Benchmarks

  • FinEval
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing prospectus clauses and fund parameters

    Output: JSON containing list of compliance gaps, status, and state graph nodes visited

    Execution harness: Python

Evaluation tools

  • LangChain · Agent Framework
  • All Hands AI · Assistants & Interfaces

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about LangChain & All Hands AI Asset Management Compliance Suite