Scaling Customer Experience with Operationalized Agentic AI - with Shezan Kazi of Dialpad

2026-04-16 · Source: The AI in Business Podcast · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Data Science & Analytics · Depth: Intermediate, extended

Summary

Shezan Kazi, Head of AI Transformation and AI Products at Dialpad, discusses the strategic deployment of autonomous AI agents in customer-facing operations. He emphasizes that AI agents should initially handle high-volume, deterministic requests, with seamless handoffs to human agents when knowledge gaps, workflow complexity, or ambiguity arise. Kazi highlights the importance of data-driven discovery to identify actual customer pain points, often differing from initial assumptions, and stresses that successful AI integration requires redesigning processes around real interaction data. He also details the necessity of confidence scoring and third-party oversight models, like Dialpad's "Guardian," to ensure safe and compliant deployment, tracking metrics such as accuracy, customer satisfaction (CSAT), and adherence to instructions to drive responsible automation and improve customer outcomes.

Key takeaway

For AI Product Managers evaluating conversational AI solutions, prioritize vendors offering robust data-driven discovery tools to align automation with actual customer needs, not just perceived ones. Focus on systems that provide clear confidence scoring and oversight models to manage human handoffs effectively, ensuring customer trust and compliance. Your implementation strategy should follow a "crawl, walk, run" approach, starting with low-risk, high-impact use cases and iteratively expanding capabilities while continuously monitoring AI CSAT and agent accuracy for scalable, long-term value.

Key insights

AI agents excel at high-volume, deterministic tasks, requiring seamless human handoff for complex or ambiguous cases.

Principles

• Prioritize data-driven discovery for automation use cases.
• Establish confidence scores and oversight models for AI agents.
• Redesign workflows for AI integration, don't just augment.

Method

Implement AI agents for initial high-volume screening, triage, and deterministic tasks. Utilize confidence scoring and real-time oversight models to determine human handoff points based on complexity, ambiguity, or non-compliance.

In practice

• Start AI automation with low-risk, high-impact tasks.
• Measure AI agent performance via accuracy and CSAT.
• Ensure seamless AI-to-human handoffs with conversation summaries.

Topics

• Agentic AI
• Customer Experience Automation
• Data-Driven Discovery
• Human-AI Handoff
• Confidence Scoring

Best for: Director of AI/ML, AI Product Manager, Consultant

Related on AIssential

• Scaling Agentic AI in CX Without Losing the Customer - with Shri Nandan of Comcast — Scaling agentic AI in CX demands robust data continuity, thoughtful human-AI orchestration, and unified cross-team governance for customer trust.
• Virgin Voyages Launches Agentic AI Crew Assistant Rovey — Agentic AI assistants can provide personalized, context-aware decision support for complex, high-consideration purchases.
• From assistants to agents — Agentic AI autonomously executes goals, shifting human-AI collaboration from reactive assistance to proactive, independent action.
• How Agentic AI and Predictive ML are Architecting the 2026 US iGaming Landscape — Agentic AI and predictive ML are autonomously managing iGaming operations, from player personalization to regulatory compliance and fraud detection.
• How this travel company's AI rollout drove a 73% satisfaction boost: A 5-step playbook for your business — Successful agentic AI deployment requires identifying business challenges, building a robust data platform, and iterative testing.
• Retailers want ‘delightfully human’ AI to do your shopping, but will the chatbots go rogue? — Agentic AI shopping assistants offer autonomy but pose risks in balancing human-like interaction with reliable performance.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The AI in Business Podcast.