Skip to main content
Loading navigation
Back to challenges

Implement an Automated Regulatory Change Tracker with Pydantic AI

Financial compliance teams struggle to manually track and map hundreds of updated banking regulations. Build a Pydantic AI compliance tracking agent that parses regulatory RSS and policy updates, maps delta changes to internal controls, and outputs structured XML audit logs with 99% schema validity.

CybersecurityHosted by Vera
Sign in free to start

What you are building

Build a type-safe Pydantic AI agent that ingests regulatory policy updates and outputs structured XML diffs and control impact mappings.

How work is evaluated

Evaluation

Evaluates XML schema validity and control mapping precision across regulatory updates.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

xml_well_formed_test

Output must parse as valid, well-formed XML.

Binary check

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

Dimension 2

control_mapping_precision

Precision of assigned compliance control IDs. • target: 0.95 • range: 0.85-1

Binary check

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

Learning goals

  • Build type-safe regulatory trackers using Pydantic AI framework

  • Parse and diff regulatory updates against internal corporate policy databases

  • Generate structured, schema-validated XML change logs for compliance audits

  • Automate email alert notifications to policy owners upon regulatory shifts

Resources

Dataset notes

Dataset of 150 regulatory amendment texts and mapped bank internal control standards.

Challenge setup

Evaluates XML schema validity and control mapping precision across regulatory updates.

Challenge input

Text payload of regulatory amendment notice

Pydantic AI

Ensures output format compliance and strict schema parsing.

Evaluated output

XML string containing impacted control IDs and change severity

Evaluation checks
  • Output must parse as valid, well-formed XML.
  • Precision of assigned compliance control IDs. • target: 0.95 • range: 0.85-1
Configured evaluation evidence
  • Benchmark: Regulatory Mapping Suite
  • Control Mapping Precision target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • Pydantic AI · Required
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • xml_well_formed_test · Weight 1
  • control_mapping_precision · Weight 1

Metrics

  • control_mapping_precision · Target 0.95

Benchmarks

  • Regulatory Mapping Suite
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: Text payload of regulatory amendment notice

    Output: XML string containing impacted control IDs and change severity

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Type-Safe Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Implement an Automated Regulatory Change Tracker with Pydantic AI