Back to Documentation
Agent Builder5 min read

Getting Started with Agent Builder

Your first AI agent in 5 minutes. Learn the basics of creating, configuring, and deploying agents.

Getting Started with Agent Builder

Overview

Create your first AI agent in just 5 minutes! This quick start guide walks you through the essential steps.

Prerequisites

  • Craveva AI account
  • A connected data source (or we'll use demo data)

Step 1: Access Agent Builder

  1. Log in to your Craveva AI dashboard
  2. Click Agent Builder in the main navigation
  3. Click Create New Agent button

Step 2: Select Data Source

  1. Choose an existing data source from the list
  2. Or click Connect New Data Source to add one
  3. For your first agent, you can use any connected database

Step 3: Schema Analysis

  1. The system automatically analyzes your data structure
  2. You'll see:
  3. Review and click Next
  • - Tables/Collections detected
  • - Fields and data types
  • - Sample data preview

Step 4: Data Mapping

  1. View the Entity Relationship graph
  2. This shows how your data tables relate to each other
  3. Use AI Assistant (optional) to filter:
  4. Click Next when ready
  • - Type: "Show only sales and customer data"

Step 5: Configure Agent

  1. Agent Name: Give it a name (e.g., "Sales Assistant")
  2. Agent Type: Choose based on your needs:
  3. Description: Briefly describe what this agent does
  4. Click Next
  • - Data Analysis: For querying and analyzing data
  • - Customer Service: For handling customer inquiries
  • - Content Generation: For creating content

Step 6: Review & Create

  1. Review all your settings
  2. Check the configuration summary
  3. Click Create Agent

Step 7: Test Your Agent

  1. You'll be taken to the agent detail page
  2. Scroll to Preview / Test section
  3. Try a sample query:
  4. Verify the response
  • - "How many sales did we have today?"
  • - "Show me the top products"

Congratulations! 🎉

You've created your first AI agent! Now you can:

  • Deploy it: Share it with your team or customers
  • Customize it: Adjust prompts and settings
  • Monitor it: Track usage and performance

Next Steps

  • Learn about [Data Mapping with AI Assistant](/documentation/guides/data-mapping-ai-assistant)
  • Explore [Deployment Options](/documentation/guides/whatsapp-integration-order-management)
  • Read [Best Practices](/documentation/best-practices)

Quick Tips

  • Start simple, then add complexity
  • Test thoroughly before deploying
  • Use descriptive agent names
  • Document what each agent does

Common First Agent Ideas

  • Sales Dashboard: "Show me today's sales"
  • Inventory Check: "What products are low in stock?"
  • Customer Lookup: "Find customer by email"
  • Product Search: "Show me all products in category X"