Skip to main content
Back to challenges
Challenge

Multi-Agent for Dynamic Price Monitoring

There is a need for transparent and consistent price monitoring. This challenge tasks you with building an advanced agent system capable of monitoring item prices across various e-commerce platforms and identifying discrepancies or non-compliance with fair pricing policies. Your agent, built using Langroid, will leverage MCP-enabled tools to dynamically scrape pricing data, analyze product information, and report on any identified inconsistencies. The system should incorporate adaptive thinking budgets to optimize resource usage during monitoring cycles.

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.

Develop an MCP-enabled agent using Langroid and Claude Sonnet 4 to dynamically monitor and report on pricing inconsistencies across e-commerce platforms.

Delivery guide

How work is evaluated

Evaluation

The evaluation will assess the agent's ability to accurately monitor prices, identify discrepancies, and provide structured reports, along with the efficiency of its adaptive thinking budget.

Datasets

Challenge datasets

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

Learning goals

What you should walk away with

  • Implement adaptive thinking budgets for efficient resource allocation.

  • Design and implement a Langroid agent with MCP for dynamic tool orchestration.

  • Integrate web scraping tools to gather real-time pricing data.

  • Utilize Claude Sonnet 4 for natural language understanding and data analysis.

  • Generate structured reports on pricing discrepancies.

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

The evaluation will assess the agent's ability to accurately monitor prices, identify discrepancies, and provide structured reports, along with the efficiency of its adaptive thinking budget.

Challenge input

{'products': [{'name': 'Product A', 'expected_price': 100, 'urls': ['url1', 'url2']}]}

Agent execution

No agent tool is listed for this challenge.

Evaluated output

{'product_name': 'Product A', 'discrepancies': [{'url': 'url1', 'observed_price': 95, 'expected_price': 100, 'status': 'underpriced'}]}

Evaluation checks
  • Output must adhere to the specified JSON format.
  • Agent must identify at least 80% of known price discrepancies in the test set.
Configured evaluation evidence
  • TokenEfficiency target: 1500
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

  • Output must adhere to the specified JSON format.
  • Agent must identify at least 80% of known price discrepancies in the test set.

Metrics

  • TokenEfficiency · Target 1500
  • MonitoringLatency · Target 15

Workflow tasks

  1. Task 1

    Input: {'products': [{'name': 'Product A', 'expected_price': 100, 'urls': ['url1', 'url2']}]}

    Output: {'product_name': 'Product A', 'discrepancies': [{'url': 'url1', 'observed_price': 95, 'expected_price': 100, 'status': 'underpriced'}]}

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Multi-Agent for Dynamic Price Monitoring