Modifying the default Web Search and Web Scrap tools settings

As an administrator, configure the Web Search and Web Scrap tools to help agents retrieve external information from web sources and present the extracted content conversationally through the Employee Navigator interface. This setup improves support efficiency and enhances the overall user experience.

The Web Scrap tool doesn't work independently. It relies on the URLs retrieved by the Web Search tool to generate responses.

Out-of-the-box Web Search and Web Scrap tools are available, and you cannot modify them directly. However, you can create new Web Search and Web Scrap tools to modify their default configurations.

Before you begin

Make sure you have cloned an out-of-the-box agent, because you can only add a custom tool to a cloned out-of-the-box agent.

For more information, see Cloning an agent.

To modify the default Web Search tool settings

1. Add a new tool in your environment. For more information, see Adding tool and toolkit for an AI Agent.
   The new tool must replicate the field value configuration of the existing out-of-the-box Web Search tool.
2. In the Configuration field, modify the following settings:

   Setting	Description
   process_name	The name of the unique identifier for the process. For this tool, it is com.bmc.dsom.hgm:Web Search.
   input_parameters	The input fields, including the parameter name, description, and type for the tool.
   output	The output fields returned by the tool.

   Default configuration:

   {
     "process_name": "com.bmc.dsom.hgm:Web Search",
     "input_parameters": [
       {
         "name": "Query",
         "description": "The search query string ",
         "type": "str"
       }
     ],
     "output": [
       "Result"
     ]
   }
3. Click Save.

To modify the default Web Scrap tool settings

1. Add a new tool in your environment. For more information, see Adding tool and toolkit for an AI Agent.
   The new tool must replicate the field value configuration of the existing out-of-the-box Web Scrap tool.
2. In the Configuration field, modify the following settings:

   Setting	Description
   customer_acknowledges_legal_responsibility	A Boolean value that confirms the customer administrator acknowledges legal responsibility for web search. This value must be set to true for the tool to operate.
   user_agent	A custom User-Agent header for HTTP requests.
   allowed_domains	A list of allowed domain patterns with wildcard support. Allowed domains support wildcards (*) at any position. If this field is empty, all domains are allowed (subject to the blocklist).
   blocked_domains	A list of blocked domain patterns with wildcard support. Blocked domains support wildcards (*) at any position. Domains matching these patterns are blocked even if they appear in the allowlist.
   max_documents	The number of documents processed from the URLs list.
   content_size_limit_mb	The content size in megabytes per webpage to prevent processing oversized content.
   get_page_timeout	The HTTP request timeout in seconds before the request ends.

   Default configuration:

   {
       "customer_acknowledges_legal_responsibility": false,
       "user_agent": "",
       "allowed_domains": [],
       "blocked_domains": [],
       "max_documents": 3,
       "content_size_limit_mb": 1.0,
       "get_page_timeout": 10
   }
3. Click Save.

Where to go from here

Adding tool and toolkit for an AI Agent