Skip to main content
Back to challenges
Challenge

Boost Generative AI Product Engagement

The challenge of user engagement and cost-effectiveness for innovative generative AI products is paramount. This challenge involves building a multi-agent system designed to act as a 'Product Growth Strategist' for a hypothetical generative AI media platform. The system will analyze market data, user engagement metrics, and content generation costs to identify root causes for low traction and high operational expenses. You will orchestrate a team of specialized agents using CrewAI and OpenAI Swarm, allowing them to collaborate, debate, and synthesize insights. Agents will leverage GPT-5 Pro for high-level strategic thinking and Claude Sonnet 4 for creative content analysis, accessing diverse data sources (market reports, user analytics, financial data) via RAG and integrating with simulated generative media APIs using MCP. The goal is to generate actionable, data-driven recommendations to improve user engagement and optimize costs for a cutting-edge generative AI product.

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.

Orchestrate a CrewAI and OpenAI Swarm multi-agent system with GPT-5 Pro and Claude Sonnet 4 for generative AI product growth strategy, using RAG and MCP tool integration.

Delivery guide

How work is evaluated

Evaluation

The evaluation will assess the clarity, originality, and data-driven nature of the strategic recommendations generated by the agent team. Emphasis will be placed on the agents' ability to synthesize information from various sources and propose actionable solutions for engagement and cost optimization.

Datasets

Challenge datasets

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

Learning goals

What you should walk away with

  • Develop advanced RAG with LlamaIndex for comprehensive data ingestion and synthesis.

  • Utilize GPT-5 Pro and Claude Sonnet 4 for diverse analytical and creative tasks.

  • Design MCP-enabled tool integration for market research and generative media platforms.

  • Implement dynamic agent teams with OpenAI Swarm for flexible task delegation.

  • Orchestrate a role-based agent team using CrewAI for collaborative product strategy.

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

The evaluation will assess the clarity, originality, and data-driven nature of the strategic recommendations generated by the agent team. Emphasis will be placed on the agents' ability to synthesize information from v...

Challenge input

{ 'product_name': 'str', 'market_data': [{'metric': 'str', 'value': 'float', 'context': 'str'}], 'user_analytics': [{'engagement_metric': 'str', 'v...

Agent execution

No agent tool is listed for this challenge.

Evaluated output

{ 'problem_statement': 'str', 'root_cause_analysis': 'str', 'strategic_recommendations': [{'recommendation': 'str', 'impact': 'str', 'cost_benefit'...

Evaluation checks
  • The problem statement accurately captures both engagement and cost issues.
  • At least two recommendations are clearly actionable and relevant to the problem.
  • Evidence of MCP calls to simulated market data and cost APIs.
Configured evaluation evidence
  • RecommendationQuality target: 0.9
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

  • The problem statement accurately captures both engagement and cost issues.
  • At least two recommendations are clearly actionable and relevant to the problem.
  • Evidence of MCP calls to simulated market data and cost APIs.
  • Logs or summary indicate active collaboration and information exchange between different agents using CrewAI/OpenAI Swarm patterns.

Metrics

  • RecommendationQuality · Target 0.9
  • DataSynthesisDepth · Target 0.85
  • CostOptimizationPotential · Target 0.75

Workflow tasks

  1. Task 1

    Input: { 'product_name': 'str', 'market_data': [{'metric': 'str', 'value': 'float', 'context': 'str'}], 'user_analytics': [{'engagement_metric': 'str', 'value': 'float'}], 'cost_analysis': [{'cost_type': 'str', 'amount': 'float', 'details': 'str'}] }

    Output: { 'problem_statement': 'str', 'root_cause_analysis': 'str', 'strategic_recommendations': [{'recommendation': 'str', 'impact': 'str', 'cost_benefit': 'str', 'rationale': 'str'}], 'agent_collaboration_summary': 'str' }

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Boost Generative AI Product Engagement