Agents

The core building block — name, instructions, model, tools, and memory.

An Agent is the main component of ABZ Agent SDK.

It processes user input, follows the instructions you provide, and generates responses using the selected AI model.

Creating an agent only takes a few lines of code.

Create an Agent#

agent.py

from abagentsdk import Agent

agent = Agent(
    name="ABZ Assistant",
    instructions="You are a helpful AI assistant.",
    model="gemini-2.5-flash"
)

Run an Agent#

Use the run() method to send a prompt to your agent.

Python

response = agent.run("Explain what an AI agent is.")

print(response.content)

The response generated by the model is available through response.content.

Agent Parameters#

When creating an agent, you can configure different options.

Parameter	Description
`name`	Name of the agent.
`instructions`	Defines how the agent should behave.
`model`	The AI model used by the agent.
`tools`	Register function tools or built-in tools.
`memory`	Enable conversation memory.

Extending an Agent#

You can extend an agent by adding additional capabilities.

These features are optional and can be added based on your application's requirements.

Example#

math_assistant.py

from abagentsdk import Agent

agent = Agent(
    name="Math Assistant",
    instructions="Answer math questions clearly.",
    model="gemini-2.5-flash"
)

response = agent.run("What is 15 × 12?")

print(response.content)

Next Step#

Continue to Memory to learn how your agent can remember previous conversations.