Back to challenges
Challenge

Build a Sanctions and Geopolitical Trade Compliance Verifier with OpenAI Agents SDK

Create an automated trade sanctions and geopolitical compliance screening engine. Using OpenAI Agents SDK, your agent will analyze international shipping corridors, cross-reference global embargo list databases, and block non-compliant trade transactions automatically.

Workflow AutomationHosted 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 OpenAI Agents SDK compliance verifier to screen trade routes and cross-reference international embargo databases.

Delivery guide

How work is evaluated

Evaluation

Evaluate accuracy of sanction list entity matching and embargoed port screening.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

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

zero_false_negative_sanctions

All known sanctioned entities are successfully flagged with zero missing flags

Binary check

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

Dimension 2

screening_f1_score

F1 score for trade transaction clearance • 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

What you should walk away with

  • Implement OpenAI Agents SDK function calling for real-time sanction list lookups

  • Build trade route risk models for shadow-fleet and restricted maritime entities

  • Automate generation of OFAC/UN compliant transaction approval records

  • Validate zero false-negative performance on sanctioned entity matching

Resources and assets

Reference links and supporting material

Dataset notes

Combined dataset of global trade sanction entries (OFAC SDN list) and vessel registration records.

How this agent runs

Evaluate accuracy of sanction list entity matching and embargoed port screening.

Challenge input

JSON with vessel_imo, entity_name, destination_port

OpenAI Agents SDK

Autonomous agent logic and function tool calling framework.

Evaluated output

JSON with sanctioned_flag (bool), matching_sanction_list, action_required

Checks for
  • All known sanctioned entities are successfully flagged with zero missing flags
  • F1 score for trade transaction clearance • target: 0.98 • range: 0-1
Proof of success
  • Benchmark: Sanctions_Screening_Bench
  • Screening F1 Score target: 0.98
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • OpenAI · Required
  • Ax (Adaptive Experimentation) · Optional
  • Writer · Optional

Evaluation contract

  • zero_false_negative_sanctions · Weight 1
  • screening_f1_score · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Build a Sanctions and Geopolitical Trade Compliance Verifier with OpenAI Agents SDK