Skip to main content
Back to challenges
Challenge

Bilateral Energy Procurement Pipeline Agent using Google ADK

Saudi Aramco's 3.7 billion dollar agreement with French energy firms necessitates complex bilateral contract cross-referencing. Build a Google ADK (Agent Development Kit) agent powered by Gemini Multimodal models to extract cross-border trade terms and verify local content offset commitments.

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.

Develop a Google ADK agent leveraging Gemini 1.5 Pro to evaluate French-Saudi bilateral energy trade and local content compliance.

Delivery guide

How work is evaluated

Evaluation

Evaluates extracted IKTVA score calculations and total bilateral agreement valuation accuracy.

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

IKTVA Percentage Match

Validates local content calculation ratio.

Binary check

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

Dimension 2

Extraction Precision

Accuracy of extracted agreement terms. • target: 1 • 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

  • Build agent tools using Google Agent Development Kit (ADK) and Gemini API

  • Process multimodal bilateral contract scanned PDFs and French/English text agreements

  • Calculate In-Kingdom Total Value Add (IKTVA) offset compliance percentages

  • Generate structured trade agreement audit reports

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic agreement texts and financial allocation sheets representing Aramco's $3.7B partnerships with French engineering companies.

Challenge setup

Evaluates extracted IKTVA score calculations and total bilateral agreement valuation accuracy.

Challenge input

JSON object with agreement_text, local_spend_usd, and total_deal_usd.

Google ADK

Multimodal agent development using Gemini models

Evaluated output

JSON object with calculated_iktva_pct, total_deal_usd, and compliance_pass.

Evaluation checks
  • Validates local content calculation ratio.
  • Accuracy of extracted agreement terms. • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: GCC Bilateral Trade Intelligence Benchmark
  • Extraction Precision target: 1
  • 1 public reference case
Configured runtime
  • Python 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
  • Google ADK · Required
  • Google · Optional
  • Google Gemini · Optional

Evaluation contract

  • IKTVA Percentage Match · Weight 1
  • Extraction Precision · Weight 1

Metrics

  • Extraction Precision · Target 1

Benchmarks

  • GCC Bilateral Trade Intelligence Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with agreement_text, local_spend_usd, and total_deal_usd.

    Output: JSON object with calculated_iktva_pct, total_deal_usd, and compliance_pass.

    Execution harness: Python

Evaluation tools

  • Google ADK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Bilateral Energy Procurement Pipeline Agent using Google ADK