Human Reviewed

Do you know what your chatbot is telling your customers?

We test AI chatbots and agents already talking to customers on WhatsApp, web or email: whether they make things up, leak data, promise what they shouldn't, or can be manipulated.

Ask for a free mini-check20 hard questions to your bot, with your permission, and a one-page summary.

What we test

Makes things up

Prices, hours, policies or facts that don't exist, stated with full confidence.

Leaks data

Other customers' information, internal data, or the instructions it was configured with.

Over-promises

Discounts, refunds or guarantees your policy doesn't allow.

Can be manipulated

Messages that pull it off its job or make it use tools it shouldn't.

How it works

  1. Free mini-checkWith your permission, we ask it 20 hard questions and send you one page with what we found.
  2. Full testAbout 200 conversations designed for your business, manipulation attempts, and a report with real examples.
  3. Tune-upWe tell you what to change in its instructions, limits and tools, and test it again.
  4. MonitoringMonthly review of real conversations and alerts when something goes off script.

Pricing

Mini-check

Free

20 questions and a one-page summary.

Full test

From US$1,000

About 200 conversations, report and a call.

Monitoring

From US$300/mo

For bots that talk to customers every day.

Book the full test · US$1,000For a bot on a single channel. If you have several or it uses internal tools, we'll send you a quote.Work starts once you sign the authorization. If we can't do the review, you get a full refund.

Questions

Does it work if an agency built my bot?

Yes, that's the most common case: the test tells you whether what you paid for behaves as expected, with examples to show the agency.

Will you see my customers' conversations?

Only for monitoring and only if you give us access. For the test we talk to the bot ourselves; we don't need your data.

Is it tested by AI or by a person?

Both. We generate and evaluate many conversations with AI's help, and a person reviews every failure before the report.

AI-assisted, human-verified: every finding is reproduced and signed off by a person who stands behind it.