info_gatherer | SignalWire

Skill version of the InfoGathererAgent prefab. Collects answers to a configurable list of questions. Designed to be embedded within larger agents as a reusable capability.

Tools: start_questions, submit_answer (prefixed when using prefix parameter)

Requirements: None

Multi-instance: Yes (use prefix for unique tool names and state namespacing)

questions

list[dict]Required

List of question dictionaries with key_name, question_text, and optional confirm.

prefix

str

Prefix for tool names and state namespace. With prefix="intake", tools become intake_start_questions and intake_submit_answer, and state is stored under skill:intake in global_data.

completion_message

str

Message returned after all questions have been answered. Defaults to a built-in message prompting the agent to summarize the collected information.

from signalwire import AgentBase
class MyAgent(AgentBase):
    def __init__(self):
        super().__init__(name="assistant", route="/assistant")
        self.set_prompt_text("You are a helpful assistant.")
                # Two independent question sets on one agent
        self.add_skill("info_gatherer", {
            "prefix": "contact",
            "questions": [
                {"key_name": "name", "question_text": "What is your name?"},
                {"key_name": "email", "question_text": "What is your email?", "confirm": True}
            ]
        })
        self.add_skill("info_gatherer", {
            "prefix": "feedback",
            "questions": [
                {"key_name": "rating", "question_text": "How would you rate our service?"},
                {"key_name": "comments", "question_text": "Any additional comments?"}
            ]
        })
agent = MyAgent()
agent.serve()