on_summary | SignalWire

Callback method invoked when a post-prompt summary is received after a conversation ends. Override this method in a subclass to process summaries — for example, saving them to a CRM, triggering follow-up workflows, or logging call outcomes.

A post-prompt must be configured via set_post_prompt() for summaries to be generated.

The default implementation does nothing. You must override it in a subclass or set a set_post_prompt_url() to receive summaries at an external endpoint.

Parameters

summary

Optional[dict[str, Any]]Required

The summary object generated by the AI based on your post-prompt instructions. None if no summary could be extracted from the response.

raw_data

Optional[dict[str, Any]]Defaults to None

The complete raw POST data from the post-prompt request, including metadata like call_id and the full AI response.

Returns

None

Example

1 from signalwire import AgentBase
2 
3 class SupportAgent(AgentBase):
4     def __init__(self):
5         super().__init__(name="support", route="/support")
6         self.set_prompt_text("You are a helpful customer support agent.")
7         self.set_post_prompt("""
8             Summarize this call as JSON:
9             - intent: caller's primary intent
10             - resolved: yes/no/partial
11             - sentiment: positive/neutral/negative
12         """)
13 
14     def on_summary(self, summary, raw_data=None):
15         if summary:
16             call_id = raw_data.get("call_id") if raw_data else "unknown"
17             print(f"Call {call_id} summary: {summary}")
18             # save_to_database(call_id, summary)
19 
20 agent = SupportAgent()
21 agent.run()