You gave your voice agent a prompt, a price list and your rules. ListenFox reads every call it handles and points to the line where it quoted the wrong price, broke one of your rules or let a booking slip away.
A few minutes
Retell AI, Vapi and Bland AI connect with your API key, and each call is sent over by webhook as it ends. Built on something else? Connect Twilio or Plivo if your calls are recorded there, upload the recordings, or pick a Google Drive folder.
Connect a source
Once
Upload your agent’s prompt, price list and policies as PDF, Word, text or Markdown files, or give it your website. ListenFox drafts a one-page facts sheet. You edit it and confirm it, and nothing is checked against facts you haven’t approved.
Mark the prompt as a playbook and the rules inside it, like when to book, when to transfer and what never to offer, are checked as well.
Facts sheetConfirmed
Never waive the diagnostic fee. Transfer to a person when a caller smells gas.
Example for a sample heating and cooling company
On every call
Each recording is transcribed again with the speakers separated, so the check doesn’t rely on your agent’s own record of the call. Then it’s read for the outcome, what the caller wanted and what they asked for that the agent couldn’t offer.
Anything the agent said that contradicts your facts or your playbook is flagged with the quote, the moment it was said and the fact it broke.
Your teamCaller
Said “$69 to come out”; facts say the diagnostic visit is $89.
Example flag
Each finding comes from the call itself, so you can play the moment and hear it for yourself.
A price outside your list for the same item. “Quoted $69; price list says $89.”
Refunds, deposits, cancellations, warranties, or any rule in your playbook, stated differently on the call.
A Sunday booking when you’re closed on Sundays, or a same-day visit you don’t offer.
Saying yes to a job that’s listed as not offered, or turning down one you do offer.
Real prospects who hung up with no next step are marked Missed. What they asked for and couldn’t get is listed too.
Add yes-or-no questions in plain words, such as “Did the agent confirm the address?” Every call gets an answer.
An AI receptionist for a sample heating and cooling company, checked against the facts sheet and playbook above. Highlighted words are what got flagged.
Hi, my AC stopped cooling overnight. What do you charge to come out?
It’s $69 to come out, and we waive that if you go ahead with the repair.
Okay. Could someone come this Sunday?
Sunday works. I’ve booked a technician for 10 am.
Great, thanks.
Retell AI, Vapi and Bland AI connect directly. For ElevenLabs, Synthflow or an agent you built yourself, use the recordings: upload them, drop them in a Google Drive folder, or connect Twilio or Plivo if the calls are recorded there.
An inbound webhook, so any platform can send calls straight in, is coming soon.
All available today. Logos are trademarks of their owners; shown to indicate compatibility.
Most businesses run both: the AI picks up first and people take the harder calls. Both are checked against the same facts sheet and playbook, so you can see which side drifts.
| Kind | What was said | Agent | When |
|---|---|---|---|
| Price | “It’s $69 to come out.” | Ava (AI) | Mon 5 Oct, 0:11 |
| Hours | “Sunday works.” | Ava (AI) | Mon 5 Oct, 0:29 |
| Policy | “You get the deposit back if you cancel on the day.” | Marcus | Sun 4 Oct, 2:47 |
| Service | “Yes, we clean ducts too.” | Ava (AI) | Sat 3 Oct, 1:05 |
The policy check, outcomes, missed bookings and your own questions run on every call, whoever answered it.
Retell sends each call with the agent’s name, so its calls sit next to your team’s and you can filter by agent. Vapi and Bland calls arrive without a name for now.
A trigger can post each flag to Slack, Telegram, email or your own webhook, with the quote and the moment.
Not available yet. We’ll mark each one live on the changelog when it ships.
A brief score for each agentOne number per agent, tracked week by week as you change the prompt
Coming soonCompare prompt versionsCalls before and after a prompt change, side by side
Coming soonHandling scores for AI agentsGreeting, qualifying and resolution scores are built for people today
Coming soonTransfer checksWhether the agent handed over to a person when your rules say it should
Coming soonAgent names from Vapi and Bland AI
Coming soon
Questions about AI agentsDoes it use the transcript from my voice platform?
No. ListenFox transcribes the recording itself, with the speakers separated, so the check doesn’t depend on your agent’s own account of the call.
Will it catch every made-up answer?
No. It flags what contradicts your confirmed facts sheet and playbook. If the sheet says nothing about a topic, nothing is flagged on it, so the fuller the sheet, the more it catches.
Does it change how my agent behaves on the call?
No. It reads calls after they end and sits nowhere in your agent’s call path. Changing the prompt is up to you.
We build voice agents for clients. Can we keep them apart?
Yes. Each client can have its own workspace, with its own facts sheet, playbook and team.
What does it cost?
The same plans as for calls your team takes. See pricing.
Book a demo with your agent’s prompt and price list, and we’ll check its calls with you.