Skip to main content
Back to challenges
Challenge

Pydantic AI PLI Scheme Subsidy Compliance Agent

EV manufacturers receiving Production Linked Incentive (PLI) grants must validate domestic value addition (DVA) against strict government criteria. You will construct a type-safe compliance pipeline that parses manufacturing bills of materials and supplier invoices to compute verified grant claims.

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.

Build a Pydantic AI agent that enforces strict type validation and structural extraction over EV supply chain invoices to ensure PLI subsidy compliance.

Delivery guide

How work is evaluated

Evaluation

Evaluates DVA calculation correctness and type schema enforcement on bill-of-materials payloads.

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

DVA Minimum Threshold Test

Must reject claims with DVA below 50% target threshold

Binary check

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

Dimension 2

Type Conformance Score

100% pass rate on Pydantic field validation • target: 1 • range: 1-1

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

  • Implement Pydantic AI agent constructs with strongly-typed result types

  • Parse component invoices and calculate Domestic Value Addition (DVA) percentages

  • Enforce validation rules for component localization thresholds under Ministry PLI guidelines

  • Generate audit-ready incentive grant payout claims

Resources and assets

Reference links and supporting material

Dataset notes

Bill of Materials (BOM) entries with component pricing and supplier country certifications for EV manufacturing.

Challenge setup

Evaluates DVA calculation correctness and type schema enforcement on bill-of-materials payloads.

Challenge input

JSON with total_vehicle_cost, local_components_cost, and imported_components_cost

Pydantic AI

Provides type-safe structured outputs and validation.

Evaluated output

JSON with dva_percentage, eligible_for_pli (bool), and calculated_subsidy_amount

Evaluation checks
  • Must reject claims with DVA below 50% target threshold
  • 100% pass rate on Pydantic field validation • target: 1 • range: 1-1
Configured evaluation evidence
  • Benchmark: TypeCompliance-Bench
  • Type Conformance Score 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
  • LiveKit · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • DVA Minimum Threshold Test · Weight 1
  • Type Conformance Score · Weight 1

Metrics

  • Type Conformance Score · Target 1

Benchmarks

  • TypeCompliance-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with total_vehicle_cost, local_components_cost, and imported_components_cost

    Output: JSON with dva_percentage, eligible_for_pli (bool), and calculated_subsidy_amount

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Pydantic AI PLI Scheme Subsidy Compliance Agent