Challenge

Multi-Agent Ad Fraud Detection

This challenge tasks you with building a robust multi-agent system capable of proactively detecting, analyzing, and preventing fraudulent ad placements and scam campaigns within a simulated digital advertising platform. Leveraging cutting-edge models like Gemini 3 Pro for multimodal content analysis and Mistral Large 2 for complex policy interpretation, your system will employ a graph-based workflow for intricate decision-making and agent coordination. The solution will integrate deeply with a simulated ad platform using MCP (Model Context Protocol) for secure and efficient tool access, allowing agents to query ad creatives, target demographics, and historical performance data. Agents will communicate via A2A Protocol to collaborate on investigations, cross-referencing findings from various sources and dynamically adapting their reasoning budgets based on the severity and complexity of potential fraud cases. This setup will enable hybrid instant/deep reasoning, where simple cases are flagged quickly, while complex, evolving scam patterns trigger deeper, more resource-intensive investigations.

Workflow AutomationHosted by Vera
Challenge brief

What you are building

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

This challenge tasks you with building a robust multi-agent system capable of proactively detecting, analyzing, and preventing fraudulent ad placements and scam campaigns within a simulated digital advertising platform. Leveraging cutting-edge models like Gemini 3 Pro for multimodal content analysis and Mistral Large 2 for complex policy interpretation, your system will employ a graph-based workflow for intricate decision-making and agent coordination. The solution will integrate deeply with a simulated ad platform using MCP (Model Context Protocol) for secure and efficient tool access, allowing agents to query ad creatives, target demographics, and historical performance data. Agents will communicate via A2A Protocol to collaborate on investigations, cross-referencing findings from various sources and dynamically adapting their reasoning budgets based on the severity and complexity of potential fraud cases. This setup will enable hybrid instant/deep reasoning, where simple cases are flagged quickly, while complex, evolving scam patterns trigger deeper, more resource-intensive investigations.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
Learning goals

What you should walk away with

  • Master LangGraph for building stateful DAG agent workflows, including dynamic agent routing and checkpointing for fraud investigations.

  • Implement MCP-enabled tool integration with a simulated ad platform's APIs, leveraging Gemini 3 Pro to interpret ad creatives and metadata.

  • Design A2A Protocol communication patterns for 'Ad Auditor' and 'Policy Analyst' agents to share findings and escalate suspicious activities.

  • Deploy Gemini 3 Pro for multimodal analysis of ad images and text, identifying suspicious patterns indicative of scams or policy violations.

  • Integrate Mistral Large 2 for deep reasoning over complex ad policies and regulatory compliance, generating detailed audit reports.

  • Orchestrate hybrid instant/deep reasoning by dynamically adjusting agent 'thinking budgets' based on initial risk assessments, using a vector database for RAG over historical fraud patterns.

How this agent runs

The solution will be evaluated on its ability to accurately identify various types of ad fraud, its adherence to policy, the robustness of its multi-agent communication, and the efficiency of its reasoning process. A...

Preview configuration

Challenge input

{'ad_campaigns': [{'id': 'str', 'creative_url': 'str', 'text_content': 'str', 'target_demographics': 'list'}]}

Agent execution

The configured agent processes the input under the challenge policy.

Evaluated output

{'fraud_reports': [{'campaign_id': 'str', 'reason': 'str', 'severity': 'str', 'actions_recommended': 'list', 'investigating_agents': 'list'}]}

Checks for
  • At least 90% of critical known fraudulent ads are correctly flagged.
  • Agent logs demonstrate clear communication and handoffs using A2A Protocol for complex cases.
Proof of success
  • Fraud Detection F1 Score target: 0.85
Runtime evidence
  • Python execution harness
View technical recipe

Configured tools

No tool records are attached.

Evaluation contract

  • The evaluation module defines the checks.

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Run this agent on your dataset and AI stack

Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.

Scope a managed run
Start from your terminal
$npx -y @versalist/cli start multi-agent-ad-fraud-detection

[ok] Wrote CHALLENGE.md

[ok] Wrote .versalist.json

[ok] Wrote eval/examples.json

Requires VERSALIST_API_KEY. Works with any MCP-aware editor.

Docs
Manage API keys
Explore

Find another challenge

Jump to a random challenge when you want a fresh benchmark or a different problem space.

Useful when you want to pressure-test your workflow on a new dataset, new constraints, or a new evaluation rubric.

Frequently Asked Questions about Multi-Agent Ad Fraud Detection