What the agent did
An AI receptionist she built answers calls, books estimates on a calendar and forwards upset callers to her. A freelancer built AI customer relationship software for the business.
Result, as claimed
Inc. reports she says the automations saved her 20 hours a month. It reports the couple rebuilt revenue to $60,000 to $65,000 a month after it fell from $70,000 to $40,000, while working 80-hour weeks before the automations.
This is the result as claimed in the public source linked below. It has not been checked and is not a typical outcome.
Proof
Try it yourself
Write the call rules for an AI receptionist before you choose a tool.
Prompt
I run [type of business] and get calls about [common call types, for example quotes, service dates, complaints]. Help me write instructions for an AI phone receptionist. Include a greeting, the questions to ask for a new estimate, how to offer times from [calendar or scheduling tool], answers to these common questions [paste], and a rule to transfer any upset caller to me at [number]. List every case where it must hand over to a person. Keep it plain and short. Return the instructions only.
Prompt: starter by Solopreneur Code
Tools
- ChatGPT She began by experimenting with ChatGPT.
Steps
- List your most common call types from the last month.
- Fill in the prompt and write the handover rules first.
- Test it by playing a caller yourself, including an upset one.
- Review early calls and fix the instructions where it went wrong.
Watch out: An AI receptionist can give a wrong date or price with confidence, so keep a clear way for callers to reach a person.
Starter version by Solopreneur Code