Customer Carenumber Co / Automation & AI
I recently ran a blind A/B trial to compare GPT-assisted agent replies with responses written by experienced agents, and it taught me a lot about balancing experimental rigor with the compliance and safety needs every support operation must meet. If you’re thinking of testing generative AI in...
Read more...
When I run audits for support teams, one thing I’m always asked is: “Can we tweak the chatbot prompt and actually improve CSAT without making conversations longer?” The short answer is yes — and the way to find that single high-impact prompt is through a focused, one-week audit that...
Read more...
I’ve spent years helping support teams stitch together people, processes and platforms so that technology genuinely improves customer outcomes. When generative AI assistants enter the picture, one of the first questions I hear from teams in regulated industries is: “How do we prove what the AI...
Read more...
I ran a one-week experiment in my support team to answer a simple but important question: how do GPT-assisted agent replies affect CSAT and handle time? We’ve all seen glossy vendor decks claiming AI will cut handle times and boost satisfaction simultaneously, but in practice those goals can...
Read more...
When a chatbot hands a conversation off to a human and the customer leaves frustrated, nobody wins. Yet failed handoffs are common — unclear context, long wait times, repeated questions, and agents who lack the right information. Over the past decade I've helped teams turn those moments from pain...
Read more...
I recently ran a small experiment that tested generative AI replies against our existing templated responses. The goal wasn’t to prove one approach was universally better — it was to learn fast, protect our Net Promoter Score (NPS), and give agents and customers a clearly measurable experience....
Read more...
I once walked into a support ops meeting where the CSAT had slipped three points overnight and the product team wanted answers fast. Our chatbot handled a large chunk of inbound volume, so all eyes turned to it. We had no time for a full rewire, but we did have seven hours. What I’ll share below...
Read more...
When teams ask me whether they should rely on Zendesk macros or build custom automations to reduce reply time, my instinct is to say: “Test it.” The answer depends on your ticket patterns, volume, agent workflows, and technical comfort. Over the years I’ve run A/B tests across support stacks...
Read more...
I want to share a practical framework I use when designing a 30-day chatbot-to-human handoff plan that both reduces escalations and protects customer satisfaction (CSAT). I’ve seen teams rush handoffs — either dumping complex queries on agents too early, or keeping customers stuck in bot loops...
Read more...
Proactive outreach is one of those CX moves that sounds simple on paper but gets messy in execution. Over the years I’ve seen teams throw automated follow-ups at customers with mixed results — some see reopen rates drop, others create noise and frustration. In this post I’ll walk you through...
Read more...