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.

1 from signalwire import AgentBase
2 
3 class MyAgent(AgentBase):
4     def __init__(self):
5         super().__init__(name="assistant", route="/assistant")
6         self.set_prompt_text("You are a helpful assistant.")
7                 # Two independent question sets on one agent
8         self.add_skill("info_gatherer", {
9             "prefix": "contact",
10             "questions": [
11                 {"key_name": "name", "question_text": "What is your name?"},
12                 {"key_name": "email", "question_text": "What is your email?", "confirm": True}
13             ]
14         })
15 
16         self.add_skill("info_gatherer", {
17             "prefix": "feedback",
18             "questions": [
19                 {"key_name": "rating", "question_text": "How would you rate our service?"},
20                 {"key_name": "comments", "question_text": "Any additional comments?"}
21             ]
22         })
23 
24 agent = MyAgent()
25 agent.serve()