Subvolts take Learn how AI agents fix customer support by moving beyond basic bots to reliable digital workers. Oct 19, 2025 - Developers
- Learn how to build and configure production-grade AI agents for customer support tasks.
- Business
- Understand how to implement AI agents to improve customer service, reduce costs, and manage digital workers.
This episode provides a practical look at a key application of AI agents, relevant to current enterprise AI development.
#295 Fergal Reid: Why Your Bots Fail and How Agents Fix Your Customer Support
Audio streams from Craig S. Smith. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Episode #295 of Eye on AI features Fergal Reid discussing why chatbots fail and how AI agents can improve customer support. Host Craig Smith explores the transition from scripted bots to production-grade AI agents. The conversation covers agent reliability, safe configuration, management, onboarding, governance, and key success metrics like resolution rate and CSAT.
Many chatbots don't actually solve customer problems. This episode explains how smarter AI 'agents' can handle real issues across chat, email, and voice, acting like digital employees to help customers and businesses.
This episode offers practical insights for businesses struggling with customer support automation. It explains how to move beyond basic chatbots to more capable AI agents that can handle complex tasks and integrate with human teams. Listeners will learn about configuring, managing, and measuring the success of these agents. This is relevant as frontier labs like OpenAI, Google Gemini, and Anthropic are all investing heavily in agentic AI capabilities for enterprise applications.
- HostCraig S. Smith
- GuestFergal Reid
- Guest: Fergal Reid
- Title: #295 Fergal Reid: Why Your Bots Fail and How Agents Fix Your Customer Support
- Show: Eye on AI
- Length: 44 minutes
- Key Metrics: Resolution rate, CSAT, and cost per resolution
This episode is sponsored by AGNTCY. Unlock agents at scale with an open Internet of Agents.
Visit https://agntcy.org/ and add your support.
Why do so many chatbots fail in the real world, and how can AI agents actually fix customer support?
In this episode of Eye on AI, host Craig Smith explores how teams move beyond scripted bots to production-grade AI agents that resolve real issues across chat, email, and voice. We look at what makes agents reliable at scale, how to configure them safely, and how to manage them like digital workers alongside your human team.
Learn how leading companies approach agent onboarding and governance, which pitfalls to avoid, and which metrics matter most for success, including resolution rate, CSAT, and cost per resolution. You will also hear how to enable actions like refunds and returns through secure procedures, design human handoff that customers appreciate, and build an omnichannel rollout plan that scales responsibly.
Stay Updated: Craig Smith on X:https://x.com/craigss Eye on A.I. on X: https://x.com/EyeOn_AI
55 min42 min51 min34 minUkraine's Secret Weapon: The Points System Winning the Drone War | Andrii Hrytseniuk
WithAndrii Hrytseniuk
Same guests, other shows
1 h 34The Customer Service Revolution: Building Fin, with Eoghan McCabe & Fergal Reid of Intercom
WithEoghan McCabe, Fergal Reid
Questions people ask
- Why do most chatbots fail?
- Many chatbots fail because they are scripted and cannot handle real-world issues or complex customer needs.
- How can AI agents improve customer support?
- AI agents can resolve real issues across chat, email, and voice, acting like digital workers alongside human teams.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Craig S. Smith.