Skip to main content
Loading navigation
Back to challenges

Multilingual KYC Proof-of-Address Verification Engine with Claude Agents SDK

Cross-border payment expansion across Africa and emerging markets requires verifying identity and proof-of-address documents issued in diverse formats, languages, and character scripts (e.g. Arabic, French, Swahili, Amharic). Standard static OCR templates fail on non-standard utility bills. In this challenge, you will implement a multilingual proof-of-address verification agent using the Claude Agents SDK. The agent will analyze unstructured visual document scans, perform translation and entity extraction, and verify address details against customer registration databases.

CybersecurityHosted by Vera
Sign in free to start

What you are building

Develop a multilingual proof-of-address verification agent using Claude Agents SDK to parse non-standard global utility bills.

How work is evaluated

Evaluation

Evaluates address extraction accuracy and matching decisions across multilingual utility bill images.

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

address_match_pass

Verifies match confidence is above 0.90 for valid documents

Binary check

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

Dimension 2

address_extraction_accuracy

Accuracy of extracted address string across global test samples • target: 95 • range: 0-100

Binary check

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

Learning goals

  • Initialize Claude Agents SDK with vision capabilities enabled

  • Parse unstructured multilingual utility bills (water, power, telecom)

  • Extract standardized street address, city, and date fields across French and Swahili inputs

  • Calculate fuzzy matching metrics against user-declared registration profiles

Resources

Dataset notes

Synthetic global utility bill image samples in French, Swahili, and Arabic with corresponding ground-truth text annotations.

Challenge setup

Evaluates address extraction accuracy and matching decisions across multilingual utility bill images.

Challenge input

JSON containing document_image_base64 and user_declared_address

Claude Agents SDK

Anthropic's agent SDK leveraging Claude's multimodal vision features.

Evaluated output

JSON containing extracted_address, match_confidence, and onboarding_verdict

Evaluation checks
  • Verifies match confidence is above 0.90 for valid documents
  • Accuracy of extracted address string across global test samples • target: 95 • range: 0-100
Configured evaluation evidence
  • Benchmark: FinMultilingual-KYC-Bench
  • Address Extraction Accuracy target: 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
  • Claude Code · Required
Observation
  • Claude Code · Required
Policy Serving
  • Claude 4.1 Opus · Optional
  • Claude 4 Sonnet · Optional

Evaluation contract

  • address_match_pass · Weight 1
  • address_extraction_accuracy · Weight 1

Metrics

  • address_extraction_accuracy · Target 95

Benchmarks

  • FinMultilingual-KYC-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing document_image_base64 and user_declared_address

    Output: JSON containing extracted_address, match_confidence, and onboarding_verdict

    Execution harness: Python

Evaluation tools

  • Claude Agents SDK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Multilingual KYC Proof-of-Address Verification Engine with Claude Agents SDK