Skip to main content
Loading navigation
Back to challenges

Build an ADNOC Gas Megaproject Allocator with Vercel AI SDK & Claude 4 Sonnet

Allocating sub-contracts across $8.2bn in gas infrastructure demands optimal multi-tier vendor matching. Build a web-integrated tool using Vercel AI SDK and Claude 4 Sonnet to automate contractor workload balancing and ensure local content compliance.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Utilize Vercel AI SDK and Claude 4 Sonnet to construct a dynamic procurement allocation dashboard for major upstream gas projects.

How work is evaluated

Evaluation

Evaluates contract package distribution and adherence to minimum ICV target scores.

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

vendor_selection_check

Verify chosen vendor meets ICV threshold >= 80

Binary check

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

Dimension 2

icv_optimization_index

Efficiency index of ICV maximization • target: 0.95 • range: 0.8-1

Binary check

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

Learning goals

  • Build real-time package assignment interfaces with Vercel AI SDK tool calling

  • Utilize Claude 4 Sonnet for complex reasoning over multi-billion dollar EPC budgets

  • Enforce In-Country Value (ICV) scoring thresholds in contract allocation

  • Generate automated contract distribution maps for supply chain managers

Resources

Dataset notes

Upstream gas project contract specifications, vendor prequalification scores, and ICV audit certifications.

Challenge setup

Evaluates contract package distribution and adherence to minimum ICV target scores.

Challenge input

JSON containing vendor bids and contract packages

AI SDK

Vercel framework for edge-ready AI application development

Claude 4 Sonnet

High reasoning capabilities for complex contract evaluations

Evaluated output

JSON package allocation map

Evaluation checks
  • Verify chosen vendor meets ICV threshold >= 80
  • Efficiency index of ICV maximization • target: 0.95 • range: 0.8-1
Configured evaluation evidence
  • Benchmark: ProcurementOptBench
  • Icv Optimization Index target: 0.95
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript 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
  • Vercel AI SDK · Optional
  • aiXplain · Optional
Policy Serving
  • Claude 4 Sonnet · Required
Orchestration
  • Vercel AI SDK · Optional

Evaluation contract

  • vendor_selection_check · Weight 1
  • icv_optimization_index · Weight 1

Metrics

  • icv_optimization_index · Target 0.95

Benchmarks

  • ProcurementOptBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing vendor bids and contract packages

    Output: JSON package allocation map

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · Agent SDK
  • Claude 4 Sonnet · LLM Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an ADNOC Gas Megaproject Allocator with Vercel AI SDK & Claude 4 Sonnet