Experimental Seat Booking Agent
Experimental Seat Booking Agent implementation using OpenAI Agents SDK and Autogen memory and MCP tools support
What is the Experimental Seat Booking Agent?
The Experimental Seat Booking Agent is a self-service airline seat reservation kiosk that utilizes OpenAI Agents SDK, Autogen extensions, and MCP tools to provide comprehensive customer support for flight seat bookings.
How to use the Experimental Seat Booking Agent?
To use the agent, set up the environment by creating a virtual environment and installing the required packages. Then, run the application using the command chainlit run app.py.
Key features of the Experimental Seat Booking Agent?
- Triage agent to answer general inquiries and route questions to specialized agents.
- Retrieve user preferences on seating, airlines, and food.
- Use MCP server tools for web content fetching and file reading.
- Specialized QA agent for questions about planes, flights, and onboarding.
- Web chat interface for user self-service.
Use cases of the Experimental Seat Booking Agent?
- Assisting customers with seat reservations at self-service kiosks.
- Providing information about flights and onboarding processes.
- Handling customer inquiries through a call center interface.
FAQ from the Experimental Seat Booking Agent?
- Can the agent handle all types of inquiries?
Yes, the agent is designed to triage and route inquiries to specialized agents based on the user's needs.
- Is there a web interface for users?
Yes, the agent includes a web chat interface for self-service.
- What technologies are used in this project?
The project uses Linux, OpenAI Agents SDK, Autogen, Chainlit, and more.
Experimental Seat Booking Agent
Experimental seat booking agent implementation combines OpenAI Agents SDK, Autogen extensions, and MCP tools support.
Use Case
The self-service airline seat reservation kiosk, also known as a flight seat booking service agent or passenger service agent, is designed to provide comprehensive customer support and assistance. This kiosk ensures a smooth and positive travel experience by handling various tasks, including reservations, through its call center interface.
Key Features:
- Triage agent answer user general inquiry with tools
- Triage agent should route customer question to specialized agents
- Triage agent retrieve user preferences on seating, airlines and food
- Triage agent use agents as tools on question routing
- Triage agent use MCP server as tools to perform web fetch content and read files system
- QA agent has knownledge to handling questions about Plane, Flight and Onboarding
- Seat booking agent specifilized on plane seat reservation tasks
- Web Chat interface for user self-service
Lab Technical Stack
- Linux
- OpenAI Agents SDK
- Autogen 0.4 + extensions (MCP Tools,OpenAI, Ollama)
- Chainlit (UI)
- Ollama (local Qwen2,5)
Environment
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Running
chainlit run app.py
Todos
- save seat history at the end of the booking
- improve FAQ agent to use RAG on actual documents
- improve memory storage
- add MCP tools to invoke actual booking service api
- more to came...
Contributing
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
Important: Please keep your pull requests small and focused. This will make it easier to review and merge.
Feature Requests
If you have a feature request, please open an issue and make sure it is tagged with enhancement.
License
This project is licensed under the MIT License - see the LICENSE file for details.