Skip to main content

Overview

In this guide, youโ€™ll build a flight booking agent that works like a personal travel assistant. Hereโ€™s what it does:
  • Searches Google and airline websites for the best flights
  • Analyzes options and picks the top recommendations
  • Sends you an approval email before booking anything
  • Charges your card and confirms your booking
Youโ€™ll learn how to build actions (search, scrape, book), connect two agents that work together, and deploy everything to production with one command. Time: 10 minutes โ€ข Level: Beginner

Prerequisites

1

Install Ziet

2

Set your API key

Create a key in the dashboard

Step 1: Create Your Actions

Create a file called flight_agent.py:

Step 2: Create Your Agents

Add the agent classes to flight_agent.py:

Step 3: Test Locally

Test your agent locally before deploying:
This runs your agent in local mode with test data. Youโ€™ll see:
  • Actions being called
  • Memory operations
  • Integration calls (mocked locally)
  • Agent handoffs
  • Strategy execution
Expected output:

Step 4: Deploy to Production

Deploy your agent with one command:
Output:

Step 5: Invoke Your Agent

Via API

Via CLI

Via Python SDK

Via Dashboard

  1. Go to dashboard.ziet.ai
  2. Navigate to Agents โ†’ research_agent
  3. Click Run Agent
  4. Fill in the input form:
    • origin: โ€œSFOโ€
    • dest: โ€œNYCโ€
    • date: โ€œ2024-12-25โ€
    • user_email: โ€œyour@email.comโ€
  5. Click Execute

Next Steps

Actions

Deep dive into actions

Agents

Master agent orchestration

Strategies

Learn orchestration strategies

Integrations

Explore all available integrations

Common Patterns

Set in dashboard: Developer โ†’ Environment Variables

Need Help?

Join Discord

Get help from the community

Email Support

Contact the team directly