{"id":504,"date":"2025-07-16T11:21:32","date_gmt":"2025-07-16T11:21:32","guid":{"rendered":"https:\/\/codingwithramin.com\/?p=504"},"modified":"2025-08-04T09:53:53","modified_gmt":"2025-08-04T09:53:53","slug":"beyond-basic-web-search-building-specialized-ai-agent-with-bing-custom-search","status":"publish","type":"post","link":"https:\/\/codingwithramin.com\/?p=504","title":{"rendered":"Beyond Basic Web Search: Building a Specialized AI Agent with Bing Custom Search"},"content":{"rendered":"\n

When building AI agents for enterprise applications, standard web search often returns irrelevant results that compromise the quality of your solution. During a recent client project, our team needed an AI assistant capable of providing developers with specific documentation and code samples. While Bing Search returned results from various sources including outdated forum posts and unofficial tutorials, we required focused, authoritative content from trusted developer resources.<\/p>\n\n\n\n

This challenge led us to implement Bing Custom Search\u2014a powerful solution for grounding AI models within a curated content ecosystem. The impact on our specialized AI assistants has been transformative, enabling domain-specific expertise that consistently delivers accurate results.<\/p>\n\n\n\n

If you’ve read my previous post about migrating from Bing Search APIs to Azure OpenAI Agent grounding, you’ll recall how we established basic web search capabilities. Today, I’ll demonstrate how to create truly specialized agents using Bing Custom Search.<\/p>\n\n\n\n

Why Custom Search Transforms AI Agent Development<\/strong><\/h2>\n\n\n\n

Regular web search serves general-purpose queries effectively. However, when developing AI agents for specific domains, unrestricted internet access often hinders rather than helps. Domain-specific agents require expert-level knowledge within their specialized area.<\/p>\n\n\n\n

This became evident during our project. Our AI agent consistently referenced outdated Stack Overflow answers and third-party tutorials containing inaccuracies. The client identified multiple instances where the agent provided deprecated solutions, impacting developer productivity and trust in the system. We invested significant resources filtering noise and validating responses.<\/p>\n\n\n\n

Custom search addresses these challenges by creating focused search experiences limited to trusted sources. Think of it as providing your AI agent with a curated reference library rather than unrestricted internet access.<\/p>\n\n\n\n

Setting Up Your Custom Search Instance<\/h2>\n\n\n\n

Before we dive into the code, let’s get our Custom Search instance configured. We’re going to create a dedicated “Grounding with Bing Custom Search” resource in Azure. This is specifically designed for AI agent integration.<\/p>\n\n\n\n

Step 1: Creating the Grounding with Bing Custom Search Resource<\/h3>\n\n\n\n

First, create the Azure resource that will host your custom search configurations. Navigate to the Azure Portal and search for “Grounding with Bing Custom Search”. Configure the resource as follows:<\/p>\n\n\n\n

    \n
  • Click “Create” to start setting up your resource <\/li>\n\n\n\n
  • Choose your subscription and resource group (I recommend using the same resource group as your AI Foundry project) <\/li>\n\n\n\n
  • Give it a descriptive name like “MyApp-CustomSearch-Grounding” <\/li>\n\n\n\n
  • Select your region (Global is typically fine) <\/li>\n\n\n\n
  • Choose your pricing tier based on expected usage<\/li>\n\n\n\n
  • Review your settings and click “Create”<\/li>\n\n\n\n
  • Once deployed, you’ll have an empty resource ready for configuration<\/li>\n<\/ul>\n\n\n\n
    \"\"<\/figure>\n\n\n\n

    This approach ensures everything remains managed within Azure, providing integrated authentication and consolidated billing.<\/p>\n\n\n\n

    Step 2: Creating Your Custom Search Configuration<\/h3>\n\n\n\n

    After resource deployment, create your search configurations:<\/p>\n\n\n\n

      \n
    1. Navigate to Configurations<\/strong>:\n
        \n
      • Go to your newly created resource in the Azure Portal<\/li>\n\n\n\n
      • In the left navigation, under “Resource Management”, click on “Configurations”<\/li>\n\n\n\n
      • Click “Create new configuration<\/strong>“<\/li>\n<\/ul>\n<\/li>\n\n\n\n
      • Define Your Search Scope<\/strong>: Now comes the fun part – defining what your search will include: Allowed domains<\/strong>: These are the domains your search will actively include. For a developer-focused agent, I typically add:\n
          \n
        • docs.microsoft.com<\/li>\n\n\n\n
        • learn.microsoft.com<\/li>\n\n\n\n
        • github.com\/Microsoft<\/li>\n\n\n\n
        • devblogs.microsoft.com<\/li>\n<\/ul>\n<\/li>\n\n\n\n
        • Blocked domains<\/strong>: Sites you explicitly want to exclude. I always block low-quality content farms and sites known for outdated information. Slices<\/strong>: You can create different “slices” of your search for different types of content. For example, one slice for official documentation, another for code samples, and another for community discussions.<\/li>\n\n\n\n
        • Save Your Configuration<\/strong>:\n
            \n
          • Once you’ve defined your search scope, save the configuration<\/li>\n\n\n\n
          • You can create multiple configurations within the same resource for different domains or use cases<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n
            \"\"<\/figure>\n\n\n\n

            Strategic domain selection is crucial. Each configuration functions as a specialized search engine tailored to your specific requirements.<\/p>\n\n\n\n

            Step 3: Connect to Your AI Foundry Project<\/h3>\n\n\n\n

            Similar to regular Bing Search grounding, establish connection with your AI Foundry project:<\/p>\n\n\n\n

              \n
            1. In your AI Foundry project, go to “Connected Resources<\/strong>“<\/li>\n\n\n\n
            2. Click “Add Connection”<\/li>\n\n\n\n
            3. Select your Grounding with Bing Custom Search<\/strong> resource<\/li>\n\n\n\n
            4. This creates a connection that your agents can use<\/li>\n\n\n\n
            5. Reference this connection name in your code (for example, “custom-search-connection”)<\/li>\n<\/ol>\n\n\n\n
              \"\"<\/figure>\n\n\n\n

              Building Your Custom Search Agent<\/h2>\n\n\n\n

              Let’s extend our previous implementation to leverage custom search capabilities instead of, or alongside, regular web search.<\/p>\n\n\n\n

              Building a Maintainable Agent Architecture<\/h3>\n\n\n\n

              The architecture has been completely redesigned for improved maintainability, testability, and scalability. Let me walk you through the enhanced design approach.<\/p>\n\n\n\n

              App settings<\/h3>\n\n\n\n

              You’ll notice I’ve moved away from separate configuration sections to an array-based approach. This makes it much easier to manage multiple agents – just add another object to the array instead of creating new top-level sections.<\/p>\n\n\n\n

              <\/circle><\/circle><\/circle><\/g><\/svg><\/span>