BedrockAgent

BedrockAgent extends AgentBase to use Amazon Bedrock’s voice-to-voice model as the AI backend. It generates SWML with the amazon_bedrock verb instead of ai, while maintaining full compatibility with all standard agent features: prompts (text and POM), skills, SWAIG functions, post-prompt, and dynamic configuration.

Extends AgentBase — inherits all parent properties and methods.

BedrockAgent generates SWML with the amazon_bedrock verb instead of ai. See the SWML bedrock reference for the full specification.

Properties

name

strDefaults to bedrock_agent

Agent name.

route

strDefaults to /bedrock

HTTP route for the agent endpoint.

system_prompt

str

Initial system prompt. Can be overridden later with set_prompt_text().

voice_id

strDefaults to matthew

Bedrock voice identifier (e.g., "matthew", "joanna").

temperature

floatDefaults to 0.7

Generation temperature. Range: 0 to 1.

top_p

floatDefaults to 0.9

Nucleus sampling parameter. Range: 0 to 1.

max_tokens

intDefaults to 1024

Maximum tokens to generate per response.

**kwargs

Any

Additional arguments passed to the AgentBase constructor (e.g., host, port).

Methods

set_voice

Set the Bedrock voice ID after construction.

set_inference_params

Update Bedrock inference parameters.

Overridden behavior

BedrockAgent overrides several AgentBase methods to adapt for the Bedrock voice-to-voice model:

Method	Behavior
`set_llm_model()`	Logs a warning and does nothing. Bedrock uses a fixed voice-to-voice model.
`set_llm_temperature()`	Redirects to `set_inference_params(temperature=...)`.
`set_prompt_llm_params()`	Logs a warning. Use `set_inference_params()` instead.
`set_post_prompt_llm_params()`	Logs a warning. Bedrock post-prompt uses OpenAI configured in the platform.

Parameters specific to text-based LLMs (barge_confidence, presence_penalty, frequency_penalty) are automatically filtered out during SWML rendering and have no effect on Bedrock agents.

Prompt methods (set_prompt_text(), set_prompt_pom(), prompt_add_section(), etc.) work normally. The prompt structure is built the same way as AgentBase and then included in the amazon_bedrock verb.

Examples

Basic Bedrock agent with a tool

from signalwire import BedrockAgent
from signalwire import FunctionResult
agent = BedrockAgent(
    name="bedrock-assistant",
    route="/assistant",
    system_prompt="You are a helpful customer service representative.",
    voice_id="joanna",
    temperature=0.5
)
# Use all standard AgentBase features
agent.prompt_add_section("Guidelines", "Be concise and professional.")
agent.add_language("English", "en-US", "rime.spore")
@agent.tool(
    description="Look up order status",
    parameters={
        "type": "object",
        "properties": {
            "order_id": {"type": "string", "description": "Order ID"}
        },
        "required": ["order_id"]
    }
)
def check_order(args, raw_data):
    order_id = args.get("order_id", "")
    return FunctionResult(f"Order {order_id} is shipped and arriving tomorrow.")
# Adjust inference parameters at runtime
agent.set_voice("matthew")
agent.set_inference_params(temperature=0.3, top_p=0.95)
if __name__ == "__main__":
    agent.run()

Multi-agent server with Bedrock

from signalwire import AgentBase, AgentServer, BedrockAgent
# Standard OpenAI-backed agent
standard_agent = AgentBase(name="standard", route="/standard")
standard_agent.set_prompt_text("You are a general assistant.")
# Bedrock voice-to-voice agent
bedrock_agent = BedrockAgent(
    name="bedrock",
    route="/bedrock",
    system_prompt="You are a voice-optimized assistant.",
    voice_id="matthew"
)
server = AgentServer()
server.register(standard_agent)
server.register(bedrock_agent)
if __name__ == "__main__":
    server.run()