Your first week with an AI agent on support chats
This checklist walks a support team through the first week of letting an AI agent answer customer messages. It is for team leads starting small and wanting to stay in control.
Runs in your browser. Nothing you enter is sent anywhere or saved.
Before you start
The first week with an AI agent decides whether your team trusts it. Rushing leads to wrong answers and nervous staff. Starting small, watching closely and fixing gaps early leads to a calm launch that your team is glad they did.
Work down the list in order, one or two lines a day. You do not need to finish every line in a single sitting. Tick each one as it is done, and keep a note of what surprised you, because those notes become next week's improvements.
Tick each one as you go. 0 of 10 done.
[ ] Write down your ten most common questions and their answers [ ] Collect your return, refund and shipping rules in one place [ ] List the situations a person must handle [ ] Pick the one teammate who watches the chats this week [ ] Start with one kind of question, such as order status [ ] Read every chat the agent handled at the end of day one [ ] Fix the answers that were wrong or too stiff [ ] Test a handover with a practice chat from a colleague [ ] Ask two customers how the reply felt, if they are happy to say [ ] Meet for fifteen minutes on day five and decide what to add next
A sensible shape for the week
Days one and two are for preparing: answers, rules and the watching teammate. Days three and four are for live chats on one narrow topic. Day five is for reading, fixing and deciding.
Resist the urge to add more topics in the middle of the week. A tidy small launch is easier to explain to your team and to your customers.
- Keep the agent to questions with a clear written answer.
- Let your team see the handed-over chats the same day.
- Write down every wrong answer and the fix you made.
FAQ
How much should I let the agent handle in week one?
Very little, on purpose. Pick one routine topic, such as where is my order, and let it handle only that. Widen the range once you have read a good number of its chats.
What if the agent gives a wrong answer?
Fix the written answer it relied on and read the other chats on that topic. Wrong answers are normal early on, and each one you fix makes the next chat better.
Do I need to tell my customers an agent is replying?
It is good practice to be honest. A short line such as, you are chatting with our AI agent and a person can step in any time, builds trust and sets the right expectation.
More free tools for customer support teams
- First-reply checklist for customer support teams
- Hand-over rules checklist for customer support teams
- Weekly chat review checklist for customer support teams
- Busy-season checklist for customer support teams
- Customer privacy checklist for customer support teams
- Do and don't guide for your agent: customer support teams
- Greeting messages for customer support teams
- After-hours replies for customer support teams
- Booking and order confirmations for customer support teams
- Reminder messages for customer support teams
- Apology and complaint replies for customer support teams
- "Let me check" replies for customer support teams
- Follow-up messages for customer support teams
- Review request messages for customer support teams
- Price and quote replies for customer support teams
- Delay and stock notices for customer support teams
- Thank-you messages for customer support teams
- Hand-over notes for customer support teams
- Ready answers for customer support teams
- Holiday and closure notices for customer support teams
- Missed enquiries calculator for customer support teams
- AI agent instructions builder for customer support teams
- Auto-reply message writer for customer support teams
- FAQ answer sheet for customer support teams
- Reply speed scorecard for customer support teams
- Is your business ready for an AI agent? Quiz for customer support teams
- Message workload planner for customer support teams
- Hours saved calculator for customer support teams
- Enquiry-to-customer value estimator for customer support teams
Read the guide: Answer support messages with an AI agent.