Scoring 100% of Customer Calls, Not One a Week, for a Highly Regulated FTSE 100 Utility
Call Coach is an AI tool that checks the quality of every customer service call and helps managers coach their agents from evidence, built as a proof of concept for a highly regulated FTSE 100 utility.
Company Overview
The client is a highly regulated FTSE 100 utility serving millions of customers. Its contact centre handles a high volume of calls every day, and the quality of those calls matters to customers and to the regulator.
Team managers are responsible for checking call quality and coaching their agents, alongside running the day to day operation.
Problem Statement
Each agent takes a large number of calls every day, but quality was checked by a manager listening back to one call per agent each week. Almost every call went unheard, and coaching rested on a small sample that might not be fair to the agent.
Outcome Delivered
Every call is now scored, not one sample per agent each week. Over 5,300 calls have been processed, each score is backed by a quote from the call, and managers can see who needs support, why, and whether the coaching worked.
Executive Overview
We built Call Coach, an AI tool that checks the quality of every customer service call and helps managers coach their agents. It reads each call, scores it against the client's own quality standards and shows the evidence behind every score.
Coverage moved from one call per agent per week to 100% of calls, with over 5,300 calls processed so far. Every agent is measured against the same bar, and a person still makes every coaching and performance decision.
Our Approach
We started from the client's own quality framework, so the tool scores what the business already cares about rather than a generic checklist. Call transcripts flow straight into Call Coach, and a user can also drop in a single call by hand to analyse it.
Trust came first. No score is a black box: each one has a confidence level and links to the exact line in the call that earned it. The tool informs managers, and people stay in charge of every decision about an agent.
Challenges
Challenges Faced
Every engagement starts with a clear-eyed view of what was actually getting in the way, because you cannot fix what you cannot see. Here we set out the real constraints the client was working within, the costs and risks they were carrying, and the gaps that needed closing before any meaningful progress could be made.
Let's Transform Your Enterprise Today
Send an EnquiryAlmost every call unheard
With one call per agent per week reviewed, the vast majority of calls were never checked.
Coaching from a small sample
One call a week may not reflect how an agent really performs, so coaching could be unfair or miss the real issue.
Different reviewers, different bars
Scores depended on who listened, so agents were not always measured against the same standard.
Managers short of time
Listening back to calls took time that managers could have spent coaching.
Deployed solutions
What We Did
A look at how we approached the work, from the first discovery sessions through to the changes we put in place, and the thinking behind each decision along the way. The aim is always the same, to deliver something measurable that the client owns and can build on, rather than a one-off fix that fades once we leave.
Every call read in full
Call Coach reads the whole conversation, split by speaker, and records talk time and call type.
Five quality pillars
Each call is scored from 0 to 3 on five pillars mapped to the business, such as creating a human connection, owning the experience and fixing things first time. Each call is also checked against the procedure for that type of call.
Evidence behind every score
Each score comes with a confidence level and a link to the line that earned it. In one example, a call about a higher bill scored 0 for human connection at 98% confidence, because the agent used jargon and the customer said they did not understand it.
Customer sentiment tracked
The customer's sentiment is followed through the call, so managers can see where a conversation turned.
A live view of the whole operation
Scores add up to a live picture of the contact centre, showing who is struggling and why, including calls likely to lead to a repeat contact.
Coaching that shows its impact
Agent scorecards, a coaching log and a coaching room turn scores into a plan for each conversation, linked to calls the agent actually took. In the demo data, one agent's score rose by more than a full point after a logged coaching session.