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.
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.
How work is evaluated
Evaluates financial valuation calculations and document retrieval precision.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
citation_validity
Ensures all citations reference existing source documents
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
npv_variance
Percentage difference between calculated NPV and gold benchmark • target: 0.05 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
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.
Reference links and supporting material
Financial reports, concession contracts, and revenue estimates for GCC stadium and leisure assets.
How this agent runs
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
- Ensures all citations reference existing source documents
- Percentage difference between calculated NPV and gold benchmark • target: 0.05 • range: 0-1
- Benchmark: FinRAG-Bench
- Npv Variance target: 0.05
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- BeeAgent · Required
- Llama Index · Optional
- Exa · Optional
Evaluation contract
- citation_validity · Weight 1
- npv_variance · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.