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.
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.
How work is evaluated
Evaluates extracted IKTVA score calculations and total bilateral agreement valuation accuracy.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
IKTVA Percentage Match
Validates local content calculation ratio.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Extraction Precision
Accuracy of extracted agreement terms. • target: 1 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
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
Reference links and supporting material
Synthetic agreement texts and financial allocation sheets representing Aramco's $3.7B partnerships with French engineering companies.
How this agent runs
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.
- Validates local content calculation ratio.
- Accuracy of extracted agreement terms. • target: 1 • range: 0-1
- Benchmark: GCC Bilateral Trade Intelligence Benchmark
- Extraction Precision target: 1
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- Google ADK · Required
- Google · Optional
- Google Gemini · Optional
Evaluation contract
- IKTVA Percentage Match · Weight 1
- Extraction Precision · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.