The agent who always
knows the answer.
Agent Copilot is a real-time AI panel embedded in Verint's contact center desktop. It reads the conversation as it happens and surfaces what the agent needs - before they have to search.
images/wrapup-after.webp
Background
Verint had best-in-class tools for routing, recording, and workforce management - but nothing for the agent in the middle of a live conversation. Agent Experience was the initiative to change that, and the Copilot panel was the bet at its center.
It started as a hackathon. The concept - a panel that reads what's happening in real time and responds with context, knowledge, and guidance - was genuinely new territory for Verint. Nothing in the existing product suite pointed toward what this should be. Getting from working prototype to production feature meant building something reliable enough to run during any live customer conversation.
The problem
Agents are expected to know everything - instantly. While a customer is talking, they hold context, search knowledge bases, stay on top of compliance requirements, manage the conversation itself, and write a wrap-up when it's done.
All of it is manual. All of it adds up. Nobody was helping the agent.
The Copilot
A dedicated panel on the right side of the agent desktop. It tracks the conversation and responds, with no search, no switching screens, no extra effort.
Three moments carry the feature. At the handover, context is already waiting: a natural-language summary of the bot conversation sits in the acceptance screen, before the agent has even taken the chat. During the conversation, answers surface before anyone asks for them. At the end, the wrap-up writes itself. Two to three minutes of manual write-up becomes a 20-second review.
Below is one real conversation, step by step, with the reasoning behind each decision.
Result
The Copilot was mature enough to ship standalone - ahead of the full Agent Experience launch. It became the first AI-first feature in Verint's contact center desktop, and the first time this category of real-time assistance was shown at Verint Engage.
What I'd do differently
Set a hard scope boundary at the start.
We had a lot of stakeholders, each with a slightly different version of what Copilot should be. Without a fixed scope and timeline locked in early, those competing visions kept surfacing mid-sprint - pulling the design in different directions and making it hard to reach a decision that stuck. A defined cutoff agreed on upfront would have given the team something to push back against, and would have made prioritization faster and cleaner.
Documented every decision in writing, every time.
We had a lot of alignment meetings - but alignment that lives only in people's heads doesn't survive the next meeting. When decisions weren't written down, they got relitigated. The same questions came back in different forms, with different people, and the design paid for it in unnecessary iterations. A simple decision log - what we decided, why, and who was in the room - would have saved significant time across the project.