Skip to main content
Back to challenges
Challenge

Enterprise AI ROI Analyzer

Develop an advanced agentic system capable of autonomously evaluating the Return on Investment (ROI) for proposed AI and automation initiatives within an enterprise setting. This challenge emphasizes architecting a sophisticated multi-agent workflow using LangGraph to navigate complex enterprise data, integrate via MCP with internal systems, and leverage the extended reasoning capabilities of GPT-5 for detailed financial modeling and risk assessment. The goal is to provide actionable insights for strategic AI investment decisions.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build a graph-based multi-agent system using LangGraph, GPT-5, and MCP for automated enterprise AI/automation ROI analysis.

Delivery guide

How work is evaluated

Evaluation

The system will be evaluated on its ability to accurately assess the ROI of a simulated AI investment project. This includes correctly identifying key financial metrics, performing valid cost-benefit analysis, and providing a comprehensive report that justifies its conclusions.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Learning goals

What you should walk away with

  • Build hybrid reasoning systems for comprehensive analysis.

  • Master LangGraph for building dynamic, adaptive agent workflows.

  • Design and deploy extended thinking pipelines with GPT-5.

  • Implement MCP for seamless enterprise system tool integration.

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

The system will be evaluated on its ability to accurately assess the ROI of a simulated AI investment project. This includes correctly identifying key financial metrics, performing valid cost-benefit analysis, and pro...

Challenge input

{'project_name': 'string', 'project_description': 'string', 'estimated_cost': 'float', 'expected_benefits': ['string'], 'simulated_enterprise_data'...

Agent execution

No agent tool is listed for this challenge.

Evaluated output

{'roi_summary': 'string', 'detailed_financial_model': 'json', 'risk_assessment': 'string', 'recommendation': 'string', 'justification': 'string'}

Evaluation checks
  • Ensure all required output fields are present and non-empty.
  • Check if the detailed financial model's calculations (e.g., ROI, payback period) are logically consistent w...
Configured evaluation evidence
  • Calculation Accuracy target: 95
Configured runtime
  • Python execution harness

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

No tool records are attached.

Evaluation contract

  • Ensure all required output fields are present and non-empty.
  • Check if the detailed financial model's calculations (e.g., ROI, payback period) are logically consistent with the input data and a plausible financial model.

Metrics

  • Calculation Accuracy · Target 95
  • Contextual Relevance · Target 4
  • Report Clarity · Target 4

Workflow tasks

  1. Task 1

    Input: {'project_name': 'string', 'project_description': 'string', 'estimated_cost': 'float', 'expected_benefits': ['string'], 'simulated_enterprise_data': {'revenue_growth_rate': 'float', 'operational_cost_reduction_potential': 'float'}}

    Output: {'roi_summary': 'string', 'detailed_financial_model': 'json', 'risk_assessment': 'string', 'recommendation': 'string', 'justification': 'string'}

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Enterprise AI ROI Analyzer