amazon_bedrock

Create an Amazon Bedrock agent with a prompt. Since the text prompt is central to getting great results out of the AI, it is highly recommended that you also read the Prompting Best Practices guide.

Properties

objectRequired

An object that accepts the following properties.

amazon_bedrock.global_data

object

A powerful and flexible environmental variable which can accept arbitrary data that is set initially in the SWML script or from the SWML set_global_data action. This data can be referenced globally. All contained information can be accessed and expanded within the prompt - for example, by using a template string.

amazon_bedrock.params

object

A JSON object containing parameters as key-value pairs.

amazon_bedrock.post_prompt

object

The final set of instructions and configuration settings to send to the agent. Accepts either a text string or a pom object array for structured prompts, plus optional tuning parameters. See post_prompt details below.

amazon_bedrock.post_prompt_url

string

The URL to which to send status callbacks and reports. Authentication can also be set in the url in the format of username:password@url. See post_prompt_url callback below.

amazon_bedrock.prompt

objectRequired

Establishes the initial set of instructions and settings to configure the agent.

See prompt for additional details.

amazon_bedrock.SWAIG

object

An array of JSON objects to create user-defined functions/endpoints that can be executed during the dialogue.

See SWAIG for additional details.

post_prompt

The post_prompt object accepts either a plain text prompt or a structured POM prompt, plus optional tuning parameters.

Regular prompt

POM prompt

post_prompt.text

stringRequired

The main identity prompt for the AI. This prompt will be used to outline the agent’s personality, role, and other characteristics.

post_prompt.temperature

number

Controls the randomness of responses. Higher values (e.g., 0.8) make output more random and creative, while lower values (e.g., 0.2) make it more focused and deterministic. Range: 0.0 to 1.0.

post_prompt.top_p

number

Controls diversity via nucleus sampling. Only tokens with cumulative probability up to top_p are considered. Lower values make output more focused. Range: 0.0 to 1.0.

post_prompt.confidence

number

Minimum confidence threshold for AI responses. Responses below this threshold may be filtered or flagged. Range: 0.0 to 1.0.

post_prompt.presence_penalty

number

Penalizes tokens based on whether they appear in the text so far. Positive values encourage the model to talk about new topics.

post_prompt.frequency_penalty

number

Penalizes tokens based on their frequency in the text so far. Positive values decrease the likelihood of repeating the same line verbatim.

post_prompt_url callback

SignalWire sends the report to your post_prompt_url as an HTTP POST.

See the Amazon Bedrock post-prompt callback webhook page for the full field reference.

Responding to post prompt requests

Answer with any 2xx status. The body is not read, so {"response": "ok"} is as good as an empty one.

Amazon Bedrock example

The following example selects Bedrock’s Tiffany voice using the voice_id parameter in the prompt. It includes scaffolding for a post_prompt_url as well as several remote and inline functions using SWAIG.

1 ---
2 version: 1.0.0
3 sections:
4   main:
5     - amazon_bedrock:
6         post_prompt_url: https://example.com/my-api
7         prompt:
8           voice_id: tiffany
9           text: |
10             You are a helpful assistant that can provide information to users about a destination.
11             At the start of the conversation, always ask the user for their name.
12             You can use the appropriate function to get weather information.
13         post_prompt:
14           text: Summarize the conversation.
15         SWAIG:
16           defaults:
17             web_hook_url: https://example.com/my-webhook
18           functions:
19             - function: get_weather
20               description: To determine what the current weather is in a provided location.
21               parameters:
22                 properties:
23                   location:
24                     type: string
25                     description: The name of the city to find the weather from.
26                 type: object
27             - function: summarize_conversation
28               description: Summarize the conversation.
29               parameters:
30                 type: object
31                 properties:
32                   name:
33                     type: string
34                     description: The name of the user.