Skip to main content
Back to challenges
Challenge

LNG Procurement & Decoupled Execution with OpenAI Agents SDK & Akash Network

Adnoc selected major contractors for a new LNG export project in the UAE. Build a decentralized, high-availability supply chain agent using OpenAI Agents SDK deployed on Akash Network to track long-lead procurement items (e.g., cryogenic exchangers) and calculate risk delays. Achieve sub-second query response and continuous uptime.

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.

Deploy an OpenAI Agents SDK application on Akash Network cloud compute to maintain decentralized tracking of LNG project supply chains.

Delivery guide

How work is evaluated

Evaluation

Tests agent latency and lead time risk calculation on decentralized compute nodes.

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

latency_check

Ensures query response completes within target threshold

Binary check

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

Dimension 2

risk_prediction_accuracy

Accuracy compared against actual historical delay patterns • target: 0.88 • 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 multi-agent turn workflows using OpenAI Agents SDK.

  • Containerize and deploy the agent workflow onto Akash Network decentralized compute.

  • Evaluate long-lead LNG equipment delivery milestones and supplier lead times.

  • Implement failover and dynamic function execution across distributed nodes.

Resources and assets

Reference links and supporting material

Dataset notes

Supplier lead time records and manufacturing milestones for LNG plant components.

Challenge setup

Tests agent latency and lead time risk calculation on decentralized compute nodes.

Challenge input

JSON order details including supplier location, promised date, and shipping status

OpenAI Agents SDK

Provides robust multi-agent orchestration.

Akash Network

Decentralized hosting infrastructure.

Evaluated output

JSON assessment with critical path delay impact in days

Evaluation checks
  • Ensures query response completes within target threshold
  • Accuracy compared against actual historical delay patterns • target: 0.88 • range: 0-1
Configured evaluation evidence
  • Benchmark: SupplyChainAgent-Bench
  • Risk Prediction Accuracy target: 0.88
  • 1 public reference case
Configured runtime
  • Docker 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
  • Akash Network · Required
  • OpenAI · Optional
  • Zed · Optional

Evaluation contract

  • latency_check · Weight 1
  • risk_prediction_accuracy · Weight 1

Metrics

  • risk_prediction_accuracy · Target 0.88

Benchmarks

  • SupplyChainAgent-Bench
  • energy

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON order details including supplier location, promised date, and shipping status

    Output: JSON assessment with critical path delay impact in days

    Execution harness: Docker

Evaluation tools

  • OpenAI Agents SDK · Agent System Framework
  • Akash Network · Inference & Model Runtime

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about LNG Procurement & Decoupled Execution with OpenAI Agents SDK & Akash Network