How to tell whether it is working
Agree what you are measuring before launch, not after. Here is what to measure, and the honest baseline to measure it against.
Agree the measure before you launch
The most common reason a business cannot tell whether its agent is working is that nobody wrote down what "working" would look like before switching it on.
Four measures cover most cases:
- How many conversations were handled without a person
- How fast first replies went out
- How many enquiries turned into bookings or orders
- How much of your team's day came back
Your own numbers are the baseline
The most honest baseline is your own figures from the month before launch. An industry average tells you nothing about your business.
Pull last month's numbers before go-live, not after. Once the agent is running, the pre-launch figure becomes impossible to reconstruct accurately.
What share can it handle without a human?
This depends far more on your business than on the AI. A clinic answering the same twenty questions automates most of them. A consultancy where every enquiry is bespoke automates far less.
We would rather scope your actual conversations and give you a grounded number than quote an average that means nothing for you. Ask during scoping.
When you see a return
The immediate, visible change is response time — messages answered in seconds at any hour, including the ones that used to sit overnight. That shows up in week one.
The commercial return depends on what those unanswered messages were worth to you. If you know roughly what an enquiry is worth and how many you were losing after hours, that arithmetic is the honest place to start.
If it is not working
Tell us early and specifically. Most "it is not working" turns out to be a scope or knowledge problem we can fix quickly, and the first weeks are exactly when it should be raised.
If it genuinely is not right for your business, we would rather establish that honestly than keep billing you. Commercial terms for ending an engagement are in the terms.
What to do when Bob gives wrong answers — most early disappointment is a knowledge base gap, and this is how to find it.
Frequently Asked Questions
Where do I see these numbers?
Ask us for the measures you agreed at scoping and we report against them. Reporting is part of the retainer, not an add-on.
Is a high automation rate always good?
No. An agent that answers everything including the conversations that should have gone to a person will show a high rate and cost you customers. Read the escalations, not just the percentage.
How soon should I judge it?
Response time, week one. Anything commercial, after you have a month of comparable volume — a two-week read across a seasonal swing tells you about the season, not the agent.
Up next
Billing and usage
What the setup fee and monthly retainer cover, what is included each month, and what happens when you go past it.
Still need help?
Our team is available Mon–Fri, 10 AM–6 PM MYT (GMT+8).