Skip to main content
Back to challenges
Challenge

Agent for Public Sector Bid Monitoring

Focusing on consolidating fragmented public sector data, this challenge involves building a sophisticated, graph-based agent system. Your system will be designed to autonomously monitor diverse government procurement portals, identify relevant RFPs (Request for Proposals), and develop preliminary bid strategies. This requires agents to navigate complex, often unstructured data sources, extracting critical information and synthesizing it into actionable intelligence. The core of the solution will be a LangGraph-driven workflow, enabling dynamic and stateful decision-making. You will leverage Gemini 2.5 Pro's 'Deep Think' mode for in-depth analysis of legal and technical documents, while OpenAI o3 will handle rapid summarization. Crucially, the system must employ MCP-enabled tool integration to 'connect' with simulated public sector APIs and web scraping tools, demonstrating robust data acquisition and processing capabilities within an adaptive reasoning framework.

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 graph-based multi-agent system using LangGraph with Gemini 2.5 Pro and OpenAI o3 for public sector opportunity monitoring and bid strategy.

Delivery guide

How work is evaluated

Evaluation

The evaluation will assess the LangGraph system's ability to accurately identify and summarize public sector opportunities, extract critical information from complex documents, and generate coherent, relevant preliminary bid strategies, demonstrating efficient use of hybrid reasoning and tool integration.

Datasets

Challenge datasets

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

Learning goals

What you should walk away with

  • Develop agents for autonomous RFP identification and analysis.

  • Generate preliminary bid strategies based on analyzed opportunities.

  • Implement hybrid instant/deep reasoning using Gemini 2.5 Pro Deep Think.

  • Master LangGraph for building dynamic, stateful agent workflows.

  • Design MCP-enabled tool integration for diverse public sector data sources.

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 2 tasks

Challenge setup

The evaluation will assess the LangGraph system's ability to accurately identify and summarize public sector opportunities, extract critical information from complex documents, and generate coherent, relevant prelimin...

Challenge input

{'rfp_document_url': 'string', 'document_type': 'pdf|docx'}

Agent execution

No agent tool is listed for this challenge.

Evaluated output

{'opportunity_id': 'string', 'title': 'string', 'agency': 'string', 'submission_deadline': 'string', 'key_requirements': ['string'], 'summary': 'st...

Evaluation checks
  • Verifies that all mandatory fields (title, deadline, requirements, summary) are extracted from the RFP docu...
  • Checks if the Bid Strategy Outline logically connects to the RFP summary and proposed company capabilities.
Configured evaluation evidence
  • InformationExtractionAccuracy target: 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

  • Verifies that all mandatory fields (title, deadline, requirements, summary) are extracted from the RFP document.
  • Checks if the Bid Strategy Outline logically connects to the RFP summary and proposed company capabilities.

Metrics

  • InformationExtractionAccuracy · Target 9
  • BidStrategyRelevance · Target 8
  • HybridReasoningEfficiency · Target 8

Workflow tasks

  1. Task 1

    Input: {'rfp_document_url': 'string', 'document_type': 'pdf|docx'}

    Output: {'opportunity_id': 'string', 'title': 'string', 'agency': 'string', 'submission_deadline': 'string', 'key_requirements': ['string'], 'summary': 'string', 'contact_info': {'name': 'string', 'email': 'string'}}

    Execution harness: Python

  2. Task 2

    Input: {'rfp_summary': 'json', 'company_capabilities': ['string']}

    Output: {'strategy_title': 'string', 'executive_summary': 'string', 'sections': [{'heading': 'string', 'content': 'string'}]}

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Agent for Public Sector Bid Monitoring