Skip to main content
Back to challenges
Challenge

Type-Safe Public Data Quality Audit Agent with Pydantic AI

Inconsistent public data feeds degrade digital public infrastructure reliability and cause cascading pipeline errors. Build a type-safe data quality auditing agent using Pydantic AI to validate regional infrastructure telemetry, enforce strict data models, and automatically generate corrective patch transformations.

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.

Construct a type-safe telemetry audit agent using Pydantic AI to validate public API data and auto-fix structural anomalies.

Delivery guide

How work is evaluated

Evaluation

Evaluates schema compliance and validation retry success rates on telemetry datasets.

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

strict_pydantic_type_match

Ensures output passes Pydantic model validation without exceptions.

Binary check

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

Dimension 2

parsing_accuracy

Percentage of corrupted attributes accurately parsed and normalized. • target: 0.98 • 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

  • Use Pydantic AI for type-safe structured data generation and validation.

  • Define strict system response contracts with Pydantic BaseModel decorators.

  • Implement automatic error recovery and dynamic data normalization routines.

Resources and assets

Reference links and supporting material

Dataset notes

Public service telemetry records with structural inconsistencies, string-encoded numerical fields, and missing fields.

Challenge setup

Evaluates schema compliance and validation retry success rates on telemetry datasets.

Challenge input

JSON containing raw_unstructured_telemetry_string.

Pydantic AI

Type-safe Python agent framework with native Pydantic integration

Evaluated output

Pydantic validated JSON object with region_id, status, metric_value, and correction_applied.

Evaluation checks
  • Ensures output passes Pydantic model validation without exceptions.
  • Percentage of corrupted attributes accurately parsed and normalized. • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: Type Safety & Schema Validation Suite
  • Parsing Accuracy target: 0.98
  • 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
  • NNI (Neural Network Intelligence) · Optional
  • Hamming · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • strict_pydantic_type_match · Weight 1
  • parsing_accuracy · Weight 1

Metrics

  • parsing_accuracy · Target 0.98

Benchmarks

  • Type Safety & Schema Validation Suite
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing raw_unstructured_telemetry_string.

    Output: Pydantic validated JSON object with region_id, status, metric_value, and correction_applied.

    Execution harness: Python

Evaluation tools

  • Pydantic AI · agent_framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Type-Safe Public Data Quality Audit Agent with Pydantic AI