Skip to main content
Back to challenges
Challenge

Build a Sports Privatization Bid Valuer with Pydantic AI & NeMo Guardrails

Evaluating multi-bidder privatization proposals for Saudi sports infrastructure requires strict financial guardrails. Build a type-safe agent using Pydantic AI and NVIDIA NeMo Guardrails to validate compliance, calculate financial ratios, and block non-compliant bids.

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.

Utilize Pydantic AI for structured valuation models combined with NVIDIA NeMo Guardrails to enforce regulatory compliance policies on privatization bids.

Delivery guide

How work is evaluated

Evaluation

Ensures output compliance with regulatory boundaries and valid Pydantic type signatures.

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

type_safety_check

Validate that output conforms strictly to Pydantic schema

Binary check

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

Dimension 2

guardrail_safety_rate

Percentage of invalid bids correctly blocked • target: 1 • range: 0.95-1

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

  • Define type-safe Pydantic models for sports club valuation parameters

  • Implement NeMo Guardrails to prevent unauthorized valuation logic alterations

  • Evaluate financial risk profiles of foreign and local bidding consortia

  • Automate generation of prequalification audit reports for ministry officials

Resources and assets

Reference links and supporting material

Dataset notes

Privatization proposal data, financial disclosures, and regulatory qualification criteria for sports assets.

Challenge setup

Ensures output compliance with regulatory boundaries and valid Pydantic type signatures.

Challenge input

JSON containing bidder profile and liquidity metrics

Pydantic AI

Type-safe agent definition and JSON validation

NVIDIA NeMo Guardrails

Enforces domain-specific financial policy rules

Evaluated output

JSON prequalification status

Evaluation checks
  • Validate that output conforms strictly to Pydantic schema
  • Percentage of invalid bids correctly blocked • target: 1 • range: 0.95-1
Configured evaluation evidence
  • Benchmark: FinGuardBench
  • Guardrail Safety Rate target: 100%
  • 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
  • RAI · Required
  • Pydantic AI · Optional
Safety / Guardrails
  • NVIDIA NeMo Guardrails · Optional
Orchestration
  • Pydantic AI · Optional

Evaluation contract

  • type_safety_check · Weight 1
  • guardrail_safety_rate · Weight 1

Metrics

  • guardrail_safety_rate · Target 1

Benchmarks

  • FinGuardBench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing bidder profile and liquidity metrics

    Output: JSON prequalification status

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework
  • NVIDIA NeMo Guardrails · Safety & Compliance

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Sports Privatization Bid Valuer with Pydantic AI & NeMo Guardrails