Skip to main content
Back to challenges
Challenge

Build PLI Scheme Incentive Compliance Auditor with OpenAI Agents SDK

EV manufacturing incentive disbursement requires strict verification of domestic value addition and localized sourcing claims. Build an autonomous audit agent using OpenAI Agents SDK to parse production invoices and yield compliance audit reports with 100% mathematical precision.

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 an automated manufacturing compliance auditor using the OpenAI Agents SDK and function tools.

Delivery guide

How work is evaluated

Evaluation

Evaluates domestic value addition percentage calculations and subsidy eligibility decisions.

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_calculation_exactness

Confirms mathematical exactness of local value share calculation

Binary check

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

Dimension 2

audit_accuracy

Accuracy score of PLI subsidy eligibility decisions • 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

  • Build autonomous compliance verification agents using the OpenAI Agents SDK

  • Implement multi-turn function calls for invoice reconciliation and calculation

  • Generate automated government PLI scheme audit compliance summaries

Resources and assets

Reference links and supporting material

Dataset notes

Simulated component bill-of-materials and supply chain invoices for electric vehicle assembly.

Challenge setup

Evaluates domestic value addition percentage calculations and subsidy eligibility decisions.

Challenge input

JSON containing local_cost_inr, imported_cost_inr, total_assembly_cost_inr

OpenAI Agents SDK

Provides function-calling agent runtime and tool execution

Evaluated output

JSON containing dva_percentage, eligible_for_subsidy, and payout_inr

Evaluation checks
  • Confirms mathematical exactness of local value share calculation
  • Accuracy score of PLI subsidy eligibility decisions • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: PLI-Audit-Bench
  • Audit 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
  • OpenAI · Required
  • Aim · Optional
  • Zed · Optional

Evaluation contract

  • dva_calculation_exactness · Weight 1
  • audit_accuracy · Weight 1

Metrics

  • audit_accuracy · Target 1

Benchmarks

  • PLI-Audit-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing local_cost_inr, imported_cost_inr, total_assembly_cost_inr

    Output: JSON containing dva_percentage, eligible_for_subsidy, and payout_inr

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build PLI Scheme Incentive Compliance Auditor with OpenAI Agents SDK