How to Build an AI Agent That Searches the Web

Josh York, Mohit Saraf

Published: Apr 22, 2025

The biggest limitation of any Large Language Model is its static knowledge cutoff. If you want to deploy a reliable voice or chat agent on the Agentic Platform, you need an agent that can retrieve real-time data. Voice AI agents powered by accurate, up-to-date information transform customer interactions by eliminating hallucinations.

In the past, this required complex RAG pipelines. Today, we show you exactly how to add web search to an AI agent natively using the Syllable Platform.

Step 1: Creating Your Agent's Prompt and Tools

Start by creating a prompt tailored to your agent's purpose. Use two powerful tools:

• Web Search ToolEnables your agent to search your website, turning it into a single source of truth for dynamic content
• Data Source Search ToolAllows your agent to pull information from a static data source, perfect for policies, warranties, or other structured content ## Step 2: Crafting Your Agent's Greeting Define the greeting your agent will use when answering calls. Keep it concise and welcoming. ## Step 3: Adding a Data Source Create your static data source for information that rarely changes, such as refund policies or warranty details. ## Step 4: Building Your Agent Navigate to Agents, create a new agent, select your prompt and greeting, and configure the Web Search and Data Source Search tools. ## Step 5: Testing Your Agent Test via text to ensure both web and data source searches function correctly. ## Step 6: Going Live with Voice Set up a voice channel and call the provided phone number to interact with your agent. Ready to build smarter agents for every idea? Start Building Your Agent Today.