Skip to main content
Back to challenges
Challenge

AI-Powered Publisher Chatbot with Ad Monetization

Develop a multi-agent system using CrewAI to power an interactive AI chatbot for publisher websites. This system will dynamically respond to user queries based on the publisher's content, suggest related articles, and intelligently integrate contextual ad placements, aiming for a revenue-sharing model. It will use Gemini 2.5 Pro for deep content understanding and generation, alongside Claude Opus 4.1 for nuanced ad content and user interaction, showcasing advanced RAG and hybrid reasoning techniques.

Special Purpose AgentsHosted 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 CrewAI-orchestrated multi-agent system combining RAG, content generation, and ad integration using Gemini 2.5 Pro and Claude Opus 4.1.

Delivery guide

How work is evaluated

Evaluation

The solution will be evaluated on the functionality of the multi-agent system, the accuracy and relevance of generated content and ads, and the overall architecture's adherence to modern agentic principles.

Datasets

Challenge datasets

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

Learning goals

What you should walk away with

  • Integrate advanced RAG techniques for real-time content retrieval and synthesis.

  • Design and implement a multi-agent system with CrewAI for complex web applications.

  • Develop agents capable of contextual ad placement and revenue optimization.

  • Orchestrate agent interactions for a seamless user experience.

  • Utilize hybrid reasoning (instant/deep) with Gemini 2.5 Pro for dynamic responses.

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

The solution will be evaluated on the functionality of the multi-agent system, the accuracy and relevance of generated content and ads, and the overall architecture's adherence to modern agentic principles.

Challenge input

{ "user_query": "string", "publisher_content": "string[]", "mock_ad_database": "object[]" }

Agent execution

No agent tool is listed for this challenge.

Evaluated output

{ "chatbot_response": "string", "suggested_ad": "object | null" }

Evaluation checks
  • Checks if CrewAI agents are properly instantiated, communicate effectively, and delegate tasks according to...
  • Verifies that chatbot responses are factually accurate and directly grounded in the provided `publisher_con...
  • Ensures the `suggested_ad` is highly relevant to the `user_query` and the `chatbot_response`'s context, bas...
Configured evaluation evidence
  • ResponseCoherence 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

  • Checks if CrewAI agents are properly instantiated, communicate effectively, and delegate tasks according to the defined workflow.
  • Verifies that chatbot responses are factually accurate and directly grounded in the provided `publisher_content`, minimizing hallucination.
  • Ensures the `suggested_ad` is highly relevant to the `user_query` and the `chatbot_response`'s context, based on keywords or semantic similarity.

Metrics

  • ResponseCoherence · Target 0.9
  • AdRelevanceScore · Target 0.8
  • ContentUtilizationRate · Target 0.75

Workflow tasks

  1. Task 1

    Input: { "user_query": "string", "publisher_content": "string[]", "mock_ad_database": "object[]" }

    Output: { "chatbot_response": "string", "suggested_ad": "object | null" }

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about AI-Powered Publisher Chatbot with Ad Monetization