Skip to main content
Back to challenges
Challenge

Privatization Valuation Agent with LlamaIndex & BeeAgent

A US-led group prequalified for Saudi sports privatization assets. Build a RAG-driven financial modeling agent using LlamaIndex and BeeAgent to index stadium yield data, concession rights, and regional privatization filings. Generate audit-ready asset valuation reports with under 5% variance against expert benchmark evaluations.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Combine LlamaIndex vector store indexing with BeeAgent structured execution to automate financial asset valuation for Saudi privatization projects.

Delivery guide

How work is evaluated

Evaluation

Evaluates financial valuation calculations and document retrieval precision.

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

citation_validity

Ensures all citations reference existing source documents

Binary check

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

Dimension 2

npv_variance

Percentage difference between calculated NPV and gold benchmark • target: 0.05 • 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

  • Index sports infrastructure financial disclosures using LlamaIndex hierarchical retrievers.

  • Design a multi-step financial analysis agent using the BeeAgent framework.

  • Perform DCF (Discounted Cash Flow) calculations based on retrieved concession terms.

  • Produce compliant financial valuation summaries with citation tracking.

Resources and assets

Reference links and supporting material

Dataset notes

Financial reports, concession contracts, and revenue estimates for GCC stadium and leisure assets.

Challenge setup

Evaluates financial valuation calculations and document retrieval precision.

Challenge input

JSON query specifying asset ID and financial assumption parameters

LlamaIndex

Provides structured retrieval for concession documents.

BeeAgent

Orchestrates step-by-step agent workflow and tools.

Evaluated output

JSON containing estimated NPV, IRR, and list of cited document IDs

Evaluation checks
  • Ensures all citations reference existing source documents
  • Percentage difference between calculated NPV and gold benchmark • target: 0.05 • range: 0-1
Configured evaluation evidence
  • Benchmark: FinRAG-Bench
  • Npv Variance target: 0.05
  • 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
  • BeeAgent · Required
  • Llama Index · Optional
  • Exa · Optional

Evaluation contract

  • citation_validity · Weight 1
  • npv_variance · Weight 1

Metrics

  • npv_variance · Target 0.05

Benchmarks

  • FinRAG-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON query specifying asset ID and financial assumption parameters

    Output: JSON containing estimated NPV, IRR, and list of cited document IDs

    Execution harness: Python

Evaluation tools

  • LlamaIndex · RAG Indexing
  • BeeAgent · Agent Systems

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Privatization Valuation Agent with LlamaIndex & BeeAgent