Skip to main content
Loading navigation
Back to challenges

Build an OpenAI Agents SDK Aadhaar Identity Verification Triage System

High-volume citizen onboarding services need rapid verification of OCR-extracted identity documents against Aadhaar metadata formatting standard constraints. Build an OpenAI Agents SDK identity verification agent that validates document tokens and flags fraudulent attempts with 98% accuracy.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Construct an identity verification agent using OpenAI Agents SDK to validate Aadhaar metadata schema structures and anomaly indicators.

How work is evaluated

Evaluation

Evaluates checksum validity verification and PII masking completeness.

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

pii_masking_check

Confirms identity numbers are properly masked

Binary check

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

Dimension 2

verification_accuracy

Accuracy of identity document authenticity decisions • 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

  • Implement OpenAI Agents SDK agents with custom tool functions for Verhoeff checksum validation

  • Detect structural anomalies in OCR extracted identity payloads

  • Enforce privacy protection masking on citizen identity numbers

  • Generate encrypted KYC audit payloads compliant with UIDAI standards

Resources

Dataset notes

Synthetic identity document OCR text Extractions and metadata records.

Challenge setup

Evaluates checksum validity verification and PII masking completeness.

Challenge input

JSON identity OCR extraction object

OpenAI Agents SDK

Agent loop execution and function calling

Evaluated output

JSON audit result with checksum_valid and masked_id

Evaluation checks
  • Confirms identity numbers are properly masked
  • Accuracy of identity document authenticity decisions • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: Identity Document Parsing Benchmark
  • Verification Accuracy target: 0.98
  • 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
  • OpenAI · Required
  • RAI · Optional
  • LangWatch · Optional

Evaluation contract

  • pii_masking_check · Weight 1
  • verification_accuracy · Weight 1

Metrics

  • verification_accuracy · Target 0.98

Benchmarks

  • Identity Document Parsing Benchmark
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON identity OCR extraction object

    Output: JSON audit result with checksum_valid and masked_id

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an OpenAI Agents SDK Aadhaar Identity Verification Triage System