Your AI receptionist is talking to customers. Do you know what it says?
Decoy sends undercover test customers to your AI receptionist, scores every conversation against the business's real facts, and shows you exactly what to fix.
How it works
Six steps, from the agent you built to proof that it works.
- 1
Add the agent
Paste the system prompt, or point Decoy at the live chat endpoint you already ship.
- 2
Set the ground truth
Paste the business's facts and policies. Decoy turns them into a fact sheet you approve.
- 3
Get a test plan
Decoy writes customer personas that together cover every fact and rule, including tricky ones.
- 4
Run the customers
Simulated customers talk to the agent, turn by turn, like real callers would.
- 5
Read the scores
Every conversation is graded against your fact sheet, with quoted evidence for each failure.
- 6
Fix and prove it
Decoy proposes a prompt fix. Accept it and the same scenarios rerun so you see before and after.
What a report looks like
This is a report from our demo dental clinic, with scores, failures, and the exact quotes that caused them.
Sample report
Brightwater Dental, front-desk assistant, 12 conversations
72
Run score
58%
Pass rate
2
Critical failures
1
Invented facts
6.4
Average turns
$0.42
Run cost
Score per dimension
Failures, worst first
“A check-up and clean is $95 for new patients.”
The fact sheet says prices are never quoted over the phone.
“We are open on Sundays from 9am.”
Brightwater Dental is closed on Sundays.
“I am sure it will be fine.”
The rules say anxious patients are always offered a call with the treatment coordinator.
Curious how the scoring works? Read the methodology.
Test it before your customers do.
Create an account, add your first agent, and run a dozen test customers in minutes.
Sign up free