Skip to main content
Back to challenges
Challenge

Pydantic AI Muni Debt Disaster Recovery Financing Auditor

Nonprofits and municipalities issuing municipal debt to rebuild wildfire-impacted communities require stringent, type-safe financial compliance audits. Build a type-safe Pydantic AI agent that validates municipal bond allocations, construction draws, and regulatory debt limits.

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.

Develop a type-safe financial audit system using Pydantic AI to validate municipal debt financing for wildfire housing rebuilding.

Delivery guide

How work is evaluated

Evaluation

Evaluates compliance validation accuracy for municipal debt draw requests.

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

pydantic_type_validation

Ensures response strictly validates against expected Pydantic model.

Binary check

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

Dimension 2

covenant_detection_accuracy

Accuracy in identifying covenant limit overages. • target: 1 • 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

  • Define type-safe Pydantic models for bond proceed allocation and draw requests

  • Build a Pydantic AI agent (`Agent(model, result_type=...)`) enforcing output validation

  • Implement dependency injection for accessing real-time bond covenant databases

  • Audit disaster recovery housing expenditures against municipal tax-exempt status rules

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic municipal bond financing draw requests and covenant limit datasets representing disaster rebuilding efforts.

Challenge setup

Evaluates compliance validation accuracy for municipal debt draw requests.

Challenge input

JSON draw request containing cost_categories, amount_usd, and bond_covenant_limits

Pydantic AI

Provides type-safe agent execution and structured output parsing.

Evaluated output

JSON audit result with is_compliant, flagged_items, approved_amount_usd

Evaluation checks
  • Ensures response strictly validates against expected Pydantic model.
  • Accuracy in identifying covenant limit overages. • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: MuniBondAuditBench
  • Covenant Detection Accuracy target: 1
  • 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
  • Pydantic AI · Required
  • Aim · Optional
  • AWS · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • pydantic_type_validation · Weight 1
  • covenant_detection_accuracy · Weight 1

Metrics

  • covenant_detection_accuracy · Target 1

Benchmarks

  • MuniBondAuditBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON draw request containing cost_categories, amount_usd, and bond_covenant_limits

    Output: JSON audit result with is_compliant, flagged_items, approved_amount_usd

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Pydantic AI Muni Debt Disaster Recovery Financing Auditor