Skip to main content
Back to challenges
Challenge

Build a Stadium Procurement Risk Inspector with Claude Agents SDK

Managing tight deadlines for $291m World Cup stadium infrastructure requires automated design and tender package auditing. Build an autonomous agent using Claude Agents SDK with extended thinking to identify scope gaps and verify compliance with FIFA infrastructure standards.

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.

Utilize Claude Agents SDK extended thinking capabilities to inspect stadium project tender packages and generate risk mitigation matrix reports.

Delivery guide

How work is evaluated

Evaluation

Evaluates the agent's ability to detect non-compliant items in stadium construction tenders.

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

violation_detection_check

Ensure non-compliance violation is flagged

Binary check

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

Dimension 2

audit_precision

Precision of compliance rule detection • target: 0.98 • range: 0.9-1

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 Claude Agents SDK runner loops with explicit extended thinking limits

  • Parse multi-disciplinary stadium design packages (structural, MEP, crowd circulation)

  • Audit contractor proposals against FIFA 2030 technical requirements

  • Generate prioritized risk scorecards for project management offices

Resources and assets

Reference links and supporting material

Dataset notes

Moroccan stadium tender notices, civil design metrics, and FIFA 2030 technical infrastructure manuals.

Challenge setup

Evaluates the agent's ability to detect non-compliant items in stadium construction tenders.

Challenge input

JSON containing stadium specs

Claude Agents SDK

Provides extended thinking models ideal for deep design verification

Evaluated output

JSON compliance report

Evaluation checks
  • Ensure non-compliance violation is flagged
  • Precision of compliance rule detection • target: 0.98 • range: 0.9-1
Configured evaluation evidence
  • Benchmark: InfrastructureAuditBench
  • Audit Precision target: 0.98
  • 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
  • StackAI · Required
  • AutoML (H2O) · Optional
  • Deepgram · Optional

Evaluation contract

  • violation_detection_check · Weight 1
  • audit_precision · Weight 1

Metrics

  • audit_precision · Target 0.98

Benchmarks

  • InfrastructureAuditBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing stadium specs

    Output: JSON compliance report

    Execution harness: Python

Evaluation tools

  • Claude Agents SDK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Stadium Procurement Risk Inspector with Claude Agents SDK