AI CSAT/NPS Survey Autocall System

Development of AI Customer Survey Autocall System (CSAT/NPS)

Voice surveys achieve 30–45% response rate vs 5–10% for email. The AI bot collects ratings, asks follow-up questions on low scores, and feeds detailed responses to analytics.

Survey Architecture

class SurveyBot:
    async def conduct_survey(self, call: ActiveCall, context: dict) -> SurveyResult:
        responses = {}

        for question in self.questions:
            # Ask question
            await call.say(question["text"].format(**context))

            # Collect response
            user_response = await call.listen(timeout_sec=10)
            parsed = await self.parse_response(user_response, question["type"])
            responses[question["id"]] = parsed

            # Conditional follow-up if low score
            if question.get("followup_if_low") and parsed.get("value", 10) <= 6:
                followup = question["followup_if_low"]
                await call.say(followup["text"])
                followup_response = await call.listen(timeout_sec=20)
                responses[f"{question['id']}_reason"] = followup_response

            # Escalate to human for critical scores
            if parsed.get("value") is not None and parsed["value"] <= 3:
                await self.escalate_to_human(call, context, responses)
                break

        return SurveyResult(...)

NPS-Specific Logic

Categorizes scores:

• 9–10: Promoter
• 7–8: Passive
• 0–6: Detractor

Analytics

Calculates NPS = (Promoters – Detractors) / Total * 100 Performs thematic analysis of open-ended responses

Timeline: NPS/CSAT bot — 2–3 weeks. With thematic analysis — 1.5 months.