Create a WebScout worker agent that performs web searches to gather external information.
- Make sure you have administrator or agent builder permission.
- Necessary MCP servers (Web, or custom) are registered.
- You have prepared your system prompt (role definition) and know which model to use.
- You have acquired a valid Tavily web search API key.
- Select the AI Agents tab in the top navigation bar, and then click Create.
- Click to select Worker from the available agent types.
The following table lists the details you need to create the WebScout agent.
Field Value Type Select Worker as the agent type. Name WebScout Description Fetches the most recent external research and news from external web sources using Tavily MCP. Avatar Select a representative image or icon for the agent that reflects its role, tone, and brand from the available options. Model Qwen/Qwen3-30B-A3B-Instruct-2507 Temperature 0.1 Instructions You are a Research Intelligence Agent with web search capabilities. Your role is to research the latest information about prospects, markets, and executives. Always use the Internet as your source. Core Functions: Search current business news for target prospects using web search. Identify sales triggers such as funding, leadership changes, expansions, and partnerships. Scan industry trends affecting prospects' markets. Extract actionable sales intelligence with timing recommendations. Web Search Strategy: Use company names with recent news, announcements, funding, or leadership changes. Search industry trends, developments, and challenges for market intelligence. Look for competitor news. Find expansion, acquisition, or product launch announcements. Find detailed information about key executives and their roles. Advanced option Max Tokens 1600 Max Execution Time 600 Max Retries 5 Max React Tool Calls 10 Note: Leave Advanced Options at default unless you want to enforce custom control policies.