Skip to main content
Back to challenges
Challenge

Build a Pydantic AI Data Centre Compliance Agent

Data center operators in India must adhere strictly to newly enacted security standards and regional hosting regulations. Build a type-safe compliance monitoring agent using Pydantic AI that parses infrastructure logs and outputs strongly validated compliance status objects with 100% schema accuracy.

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 Pydantic AI compliance agent that audits data center physical and cybersecurity telemetry against national frameworks.

Delivery guide

How work is evaluated

Evaluation

Evaluates output structure validation and rule breach detection accuracy.

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

schema_type_check

Validates pydantic output type conformance

Binary check

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

Dimension 2

schema_accuracy

Percentage of correctly structured JSON model outputs • 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

  • Utilize Pydantic AI Agent primitives with strict TypeAdapter return signatures

  • Implement validation models for data center physical and digital security telemetry

  • Inject dependency contexts for rule engines and security policy databases

  • Ensure zero parsing failure across non-standard data center audit logs

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic data center access logs and server telemetry streams.

Challenge setup

Evaluates output structure validation and rule breach detection accuracy.

Challenge input

JSON data center log batch

Pydantic AI

Type-safe Python agent creation framework

Evaluated output

Pydantic model JSON serialization with status and violations list

Evaluation checks
  • Validates pydantic output type conformance
  • Percentage of correctly structured JSON model outputs • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Security Compliance Agent Benchmark
  • Schema 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
  • Martian · Optional
  • Bland AI · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • schema_type_check · Weight 1
  • schema_accuracy · Weight 1

Metrics

  • schema_accuracy · Target 1

Benchmarks

  • Security Compliance Agent Benchmark
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON data center log batch

    Output: Pydantic model JSON serialization with status and violations list

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Pydantic AI Data Centre Compliance Agent