Agno Travel Agent: Evals with Arize AX

We will create a simple travel agent powered by the Agno framework and Anthropic models. We'll begin by installing the necessary OpenInference packages and setting up tracing with Arize AX.

Next, we'll define a set of basic tools that provide destination information, estimate trip budgets, and suggest local activities.

We will then build and run our agent, viewing the resulting trace outputs in Arize AX to understand how the agent uses its tools and reasoning.

These traces will be the foundation for our Evals Tutorial where we will:

• Run a pre-built eval
• Create a custom LLM Judge
• Run code evals

You will need an Arize AX account (with your ARIZE_API_KEY and ARIZE_SPACE_ID), an Anthropic API key, and a free Tavily API Key.

Set up keys and dependencies

Setup tracing

Define tools

First, we'll define a few helper functions to support our tools. In particular, we'll use Tavily Search to help the tools gather general information about each destination.

Our agent will have access to three tools, which we'll continue to enhance in upcoming labs:

1. Essential Info – Provides key travel details about the destination, such as weather and general conditions.

2. Budget Basics – Offers insights into travel costs and helps plan budgets based on selected activities.

3. Local Flavor – Recommends unique local experiences and cultural highlights.

Define agent

Next, we'll construct our agent. The Agno framework makes this process straightforward by allowing us to easily define key parameters such as the model, instructions, and tools.

Run agent

Finally, we are ready to run our agent! Run this cell to see examples in action.

View your traces in Arize & begin running evaluations!