InfoGathererAgent | SignalWire

Collects answers to a series of questions in sequence, with optional confirmation for critical fields. Supports both static questions (defined at construction) and dynamic questions (determined at runtime via a callback).

1 from signalwire.prefabs import InfoGathererAgent

questions

list[dict]

List of question dictionaries. If None, the agent operates in dynamic mode where questions are determined by a callback at request time. Each question dict has:

questions[].key_name

strRequired

Identifier for storing the answer (e.g., "email").

questions[].question_text

strRequired

The question to ask the user.

questions[].confirm

boolDefaults to False

If True, the agent confirms the answer with the user before proceeding. Use for critical data like email addresses and phone numbers.

name

strDefaults to info_gatherer

Agent name for identification and logging.

route

strDefaults to /info_gatherer

HTTP route for this agent.

Built-in Tools

Tool	Description	Parameters
`start_questions`	Begin the question sequence	(none)
`submit_answer`	Submit an answer and advance to the next question	`answer` (str)

Dynamic Questions

Instead of static questions, use set_question_callback() to determine questions at request time based on query parameters, headers, or request body:

1 from signalwire.prefabs import InfoGathererAgent
2 
3 def get_questions(query_params, body_params, headers):
4     question_set = query_params.get("type", "default")
5     if question_set == "support":
6         return [
7             {"key_name": "name", "question_text": "What is your name?"},
8             {"key_name": "issue", "question_text": "Describe your issue."}
9         ]
10     return [
11         {"key_name": "name", "question_text": "What is your name?"},
12         {"key_name": "message", "question_text": "How can I help?"}
13     ]
14 
15 agent = InfoGathererAgent()  # No static questions
16 agent.set_question_callback(get_questions)
17 
18 if __name__ == "__main__":
19     agent.run()

set_question_callback

callback

Callable[[dict, dict, dict], list[dict]]Required

A function receiving (query_params, body_params, headers) that returns a list of question dictionaries in the same format as the questions constructor parameter.

Accessing Collected Data

Answers are stored in global_data and available in SWAIG function handlers:

1 from signalwire import AgentBase
2 from signalwire.core.function_result import FunctionResult
3 
4 agent = AgentBase(name="assistant", route="/assistant")
5 agent.set_prompt_text("You are a helpful assistant.")
6 
7 @agent.tool(description="Process collected answers")
8 def process_answers(args, raw_data=None):
9     # Inside a tool handler
10     global_data = raw_data.get("global_data", {})
11     answers = global_data.get("answers", [])
12     # [{"key_name": "name", "answer": "John Doe"}, ...]
13     return FunctionResult(f"Processed {len(answers)} answers.")
14 
15 agent.serve()

Example

1 from signalwire.prefabs import InfoGathererAgent
2 
3 agent = InfoGathererAgent(
4     questions=[
5         {"key_name": "name", "question_text": "What is your name?"},
6         {"key_name": "phone", "question_text": "What is your phone number?", "confirm": True},
7         {"key_name": "date", "question_text": "What date would you like to schedule?"},
8         {"key_name": "time", "question_text": "What time works best for you?"}
9     ],
10     name="appointment-scheduler"
11 )
12 
13 agent.add_language("English", "en-US", "rime.spore")
14 agent.prompt_add_section("Brand", "You are scheduling appointments for Dr. Smith's office.")
15 
16 if __name__ == "__main__":
17     agent.run()