Agent Configuration

Define an agent in a JSON file or a Python dictionary and build it with the experimental config_to_agent function, so its model, prompt, and tools live in configuration rather than code. Pass a file path or a dictionary and you get back a ready-to-use Agent.

Basic Usage

Dictionary Configuration

from strands.experimental import config_to_agent

# Create agent from dictionary
agent = config_to_agent({
    "model": "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
    "prompt": "You are a helpful assistant"
})

File Configuration

from strands.experimental import config_to_agent

# Load from JSON file (with or without file:// prefix)
agent = config_to_agent("/path/to/config.json")
# or
agent = config_to_agent("file:///path/to/config.json")

Simple Agent Example

{
    "prompt": "You are a helpful assistant."
}

Coding Assistant Example

{
  "model": "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
  "prompt": "You are a coding assistant. Help users write, debug, and improve their code. You have access to file operations and can execute shell commands when needed.",
  "tools": ["strands.vended_tools.file_editor", "strands.vended_tools.shell"]
}

Configuration Options

Supported Keys

model: model ID string. Only the Amazon Bedrock model provider string form is supported here.
prompt: System prompt for the agent (string)
tools: List of tool specifications (list of strings)
name: Agent name (string)

Tool Loading

The tools configuration supports Python-specific tool loading formats:

{
  "tools": [
    "strands.vended_tools.notebook",     // Python module path
    "my_app.tools.cake_tool",            // Custom module path
    "/path/to/another_tool.py",          // File path
    "my_module.my_tool_function"         // @tool annotated function
  ]
}

The Agent class handles all tool loading internally, including:

Loading from module paths
Loading from file paths
Error handling for missing tools
Tool validation

Configuration-based agent setup only works for tools that don’t require code-based instantiation. For tools that need constructor arguments or complex setup, use the programmatic approach after creating the agent:

import http.client
from sample_module import ToolWithConfigArg

agent = config_to_agent("config.json")
# Add tools that need code-based instantiation
agent.tool_registry.process_tools([ToolWithConfigArg(http.client.HTTPSConnection("localhost"))])

Model Configurations

The model property takes a Bedrock model ID string. See AWS’s model ID reference for the available IDs. To use a different model provider, pass a model instance in the **kwargs of config_to_agent:

from strands.experimental import config_to_agent
from strands.models.openai import OpenAIModel

# Create agent from dictionary
agent = config_to_agent(
  config={"name": "Data Analyst"},
  model=OpenAIModel(
    client_args={
        "api_key": "<KEY>",
    },
    model_id="gpt-4o",
  )
)

Additionally, you can override the agent.model attribute of an agent to configure a new model provider:

from strands.experimental import config_to_agent
from strands.models.openai import OpenAIModel

# Create agent from dictionary
agent = config_to_agent(
  config={"name": "Data Analyst"}
)

agent.model = OpenAIModel(
  client_args={
      "api_key": "<KEY>",
  },
  model_id="gpt-4o",
)

Function Parameters

The config_to_agent function accepts:

config: Either a file path (string) or configuration dictionary
**kwargs: Additional Agent constructor parameters that override config values

# Override config values with valid agent parameters
agent = config_to_agent(
    "/path/to/config.json",
    name="Data Analyst"
)

Best Practices

Override with kwargs: pass Agent constructor arguments to override config values at runtime.
Rely on agent defaults: specify only the values you want to change.
Use standard tool formats: follow the Agent class conventions for tool specifications.
Handle load errors: catch FileNotFoundError and JSONDecodeError so a missing or malformed config file fails cleanly.