AI has become a standard part of customer service. As Five9’s 2026 Business Leaders Customer Experience Report found, 92 percent of organizations have implemented or piloted AI use cases in CX. But adoption alone does not guarantee a better experience.
83 percent of consumers still have to repeat themselves when moving between AI and a human agent. That's despite nearly all CX decision-makers believing their organization preserves context during the handoff.
That disconnect exposes one of the biggest challenges facing AI-powered CX: businesses are measuring whether the technology works, while customers are judging whether the experience works.
The tension is not simply that organizations are unaware of the issue. Around one third of decision-makers also acknowledge problems including customer repetition, limited agent visibility into earlier AI interactions and transfer glitches. The gap is in how success is being defined.
Sam Counterman, SVP of GTM Technology & AI Operations at Five9, told CX Today the industry needs a clearer definition of what a successful handoff actually is.
“When we move that person or that customer from A to B, whether it’s from AI to a human, that doesn’t mean that we’ve solved the problem.”
A handoff is one part of a wider customer journey, and if the transition introduces delay, loss of context, poor routing or irrelevant conversation, it can undermine the relationship with the brand.
Here are three reasons handoffs still fail, and what leaders should look for instead.
1. Organizations Measure the Transfer, Not the Outcome
Many CX teams can report whether an interaction was transferred from a virtual agent to a human, and they may also track the duration of a handoff, the volume of escalations or the percentage of contacts resolved through self-service.
Although these are useful operational measures, they do not show whether the customer’s problem was resolved.
The problem is that many organizations are grading themselves on the wrong assignment. For the customer, context is preserved only when the next person knows who they are, why they contacted the business, what they have already tried, and what should happen next.
An AI system can identify that it cannot complete a task and successfully transfer the customer to a live agent, and on an internal dashboard, the process may appear to have worked. But if the customer has to repeat their identity, explain the problem again or is routed to an agent without the required skills, the experience has failed.
“It’s more of a scoring gap, not necessarily a knowledge gap,” Counterman said. “The knowledge is there. It’s just how and when you want to use it in the right moment based on the nature of the small task or a big escalation.”
In a restaurant, being greeted at the door, shown to a table and served by different people all involve forms of handoff, where the customer does not assess each interaction separately. They assess the experience as a whole.
The same applies in customer service. A customer may start in a web chat, move to a virtual agent, transfer to voice and finally speak to a specialist. While the business may record several successful transfers, the customer may experience a fragmented journey.
This is why leaders need to move beyond channel-level measures. They should assess whether the customer reached an appropriate resolution, how much effort was required, whether the customer made repeat contact and how the interaction affected their likelihood to stay with the brand, Counterman said.
“It’s worse if you have a bad experience through handoff in a non-contextual sense with an existing brand, because that’s damaging in some ways.”
Counterman shared a recent example from a grocery order change. He started in an AI chat flow, was moved between multiple points of contact and had to repeat the same information five times.
“I managed to resolve that with the brand, but am I going to shop with them again? Probably not.”
Resolution alone did not repair the experience, as repeated explanation created friction and reduced confidence in the brand.
What does fixing it look like? Track the transfer, but treat it as the start of measurement rather than the end.
Combine transfer data with three outcome measures: repeat-contact rate in the following 24 to 48 hours, customer effort measured at the transfer point itself, and first-contact resolution after the handoff.
None of these measures is perfect in isolation. Repeat contact can have other causes, effort scores are subjective, and resolution can be defined too loosely. Together, they show whether the handoff made the customer’s situation better or worse.
Advisors should also be able to quality-score the AI handoff. They can assess whether the AI captured the correct intent, passed on usable context, escalated at the right time, and enabled them to resolve the issue without starting cold.
A handoff for a simple order amendment should not be assessed in the same way as one involving a vulnerable customer, a disputed payment or a complex healthcare query.
2. Context Gets Lost Between Systems, Channels And Teams
Context loss remains one of the most common causes of poor handoffs. The business knows who the customer is, but does not know why they are getting in contact. In more complex cases, information sits across separate applications, channels or teams. The customer’s previous conversation may be visible in one system, their account history in another and the relevant workflow in a third.
For the agent, the time to make sense of that information is limited. “Consumerism has changed, so our expectations and demands [have changed]; we want things done quicker and more effectively.”
This is why a fragmented customer record creates pressure at exactly the wrong moment, Counterman said.
“That context window is very, very short because the customer’s on the end of the phone and they’re going to want a resolution quickly.”
Context must also be applied appropriately. In regulated sectors such as financial services or healthcare, AI can support identification and routing, while human agents may need to complete validation steps. The right approach will depend on the task, the customer’s circumstances and the risk associated with the interaction.
This requires more than a transcript passed from one system to another. A useful handoff gives the next person enough information to understand the intent, the customer’s journey so far, what has already been attempted and what action should happen next. It must also support intelligent routing, Counterman noted.
“Have you got the right agents with the right skill set to be able to handle that?”
For example, a customer querying a fraud alert should not be routed through the same process as someone asking about a delivery update. Both may start with AI, but they require different levels of urgency, expertise and validation.
What fixing it looks like: Treat the customer record as a single asset rather than a collection of disconnected data points. Bring together identity, interaction history, intent, relevant account information and workflow status. Then use that context to route the case based on need, not just availability.
This is where orchestration becomes critical. Rather than simply transfering a customer from AI to a human, the goal is to intelligently orchestrate the conversation, context and next best action across AI, agents and workflows.
The agent should see a concise, relevant view of the customer’s issue, rather than having to search through multiple screens while the customer waits.
3. Knowing the Customer Isn't the Same as Understanding Their Intent
Having customer data is not enough. The organization needs recognize the customer, understand why they are getting in contact and help them reach the right resolution right away without unnecessary effort.
“The basics of it are just knowing, this is this person, and they’ve called in for this type of query. Let’s get them to the right person or even to the right channel to resolve that task,” Counterman said.
When that level of recognition is missing, customers are asked to verify their identity repeatedly, re-state their issue, or explain why they are frustrated. The handoff becomes impersonal even where the organization holds the necessary data.
There is also a risk of over-personalization. Using customer information to introduce a cross-sell before resolving the issue at hand can make the interaction feel intrusive or opportunistic.
Counterman’s advice is clear. Use the available information first to solve the customer’s immediate problem. Consider wider relationship-building activity later, when the timing is appropriate.
This is where the distinction between useful and invasive personalization becomes important. An agent may need to know that a customer has an urgent query about a delayed delivery. They may not need a full history of unrelated purchases or promotional preferences.
How can businesses fix it? Design personalization around the task in front of the customer. Give agents relevant context and clear guidance on how to use it, avoiding turning a service recovery interaction into a sales opportunity. When brands show they understand the immediate situation and act accordingly, they reduce effort and build trust.
A Successful Handoff Feels Unremarkable
The best AI-to-human handoff does not feel like a handoff at all.
Customers should not need to know whether they are interacting with AI, a human agent, or both. They should experience one continuous conversation—with the right intelligence, context and expertise brought in at the right moment.
The real measure of successful AI in CX is not whether the technology completed its part of the interaction, but whether the customer achieved the outcome they came for. As Counterman put it:
“Businesses, brands have got to be really serious about this. And not just say, ‘let’s just throw AI at it and figure it all out.’”
Five9’s 83 percent finding should be a prompt for leaders to test their own assumptions around what makes a good experience. The question is whether the customer reached a resolution without having to start again.
For more information, download the Five9 2026 Business Leaders Customer Experience Report
