Back to challenges
Challenge

Asset Management Fund Analysis Pipeline Using LlamaIndex and E2B

Asset management firms struggle to efficiently evaluate regulatory compliance and portfolio risk across Singapore fund structures following new MAS competitiveness measures. Construct a LlamaIndex RAG application executing code inside E2B sandboxes to dynamically query tax exemption rules, analyze fund metrics, and auto-generate compliance report drafts.

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.

Build an advanced RAG and code execution pipeline using LlamaIndex and E2B code sandboxes to automate MAS asset management compliance checks.

Delivery guide

How work is evaluated

Evaluation

Tests LlamaIndex extraction accuracy and E2B code execution precision when evaluating fund compliance.

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

spending_metric_check

Checks if local spending ratio calculation is mathematically accurate

Binary check

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

Dimension 2

rag_precision

Accuracy of regulatory clause references • 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

  • Implement advanced RAG indexing over MAS regulatory circulars using LlamaIndex

  • Securely execute financial calculation code within E2B sandbox environments

  • Build dynamic sub-question query engines for multi-document financial synthesis

  • Automate fund eligibility validation under Section 13O/13U tax incentive schemes

Resources and assets

Reference links and supporting material

Dataset notes

Regulatory documents and financial filings for Singapore fund vehicles evaluating MAS tax incentives.

How this agent runs

Tests LlamaIndex extraction accuracy and E2B code execution precision when evaluating fund compliance.

Challenge input

JSON with fund assets, local spending, and investor metrics

LlamaIndex

Structures regulatory documents and enables multi-step query decomposition

E2B

Executes dynamic python computations securely for fund validation

Evaluated output

JSON with qualification status, calculated metrics, and regulatory citations

Checks for
  • Checks if local spending ratio calculation is mathematically accurate
  • Accuracy of regulatory clause references • target: 0.95 • range: 0-1
Proof of success
  • Benchmark: RAG Evaluation and Code Sandbox Benchmark
  • Rag Precision target: 0.95
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Environment
  • E2B · Optional
Action Space
  • Llama Index · Required
  • E2B · Optional
  • Exa · Optional

Evaluation contract

  • spending_metric_check · Weight 1
  • rag_precision · Weight 1

Recipe state

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

Frequently Asked Questions about Asset Management Fund Analysis Pipeline Using LlamaIndex and E2B