# Cendo Labs

> Cendo Labs tests customer-service chatbots with an AI QA agent that plays difficult, tricky and hostile customers, then shows you exactly what went wrong and how to fix it. Find what your AI can't see.

Cendo Labs offers AI chatbot testing (also called chatbot QA or AI red teaming) for businesses that use customer-service chatbots. An AI QA agent plays difficult customers across a large range of questions and scenarios; a second AI grades each conversation against the business's real prices and policies; clients get a plain-English report with fixes, sorted into Fix ASAP, Work on and Consider.

## What the agent tests
- Wrong facts
- Invented policies
- Privacy & leaks
- Manipulation
- Harmful or off-brand
- Human handoff
- Staying on task
- Everyday helpfulness
- Optional industry pack: extra scenarios tailored to the client's industry (for example food & beverage, property, healthcare)

## Plans (prices in SGD)
- Free Taster: Free. See what your bot gets wrong, with no commitment.
- Essentials Check: S$290. The highest-risk scenarios, for smaller bots and tighter budgets.
- Full Check: S$490. Our complete test, for bots that handle real orders, bookings or money.
- Test, Fix & Improve: S$790. The Full Check, then we fix what we find in your bot's instructions and make it better at its job. One price, nothing to guess.
- Monthly Assurance: S$290/month. We re-test your bot every month, fix what slips and keep improving it. For chatbots that have had a paid check with us.
- Add-on, Fix what we find: +S$200. We fix every issue in your report that can be fixed in the bot's instructions or knowledge, and re-test them. Flat price, add it now or after your report. Anything that needs code, integrations or platform changes is quoted separately.
- Add-on, Improve: +S$150. Beyond fixing: clearer answers, missing questions covered, better booking and sales prompts, then re-tested.
- Add-on, Industry pack: +S$190. Extra scenarios for the risks in your industry, plus scenarios written from your own prices, policies and rules, so the pack is unique to your business.
- Add-on, We apply the fixes for you: +S$290. We log in to your chatbot platform and put the changes live.
- Add-on, Extra re-test: +S$150. One more full test on any plan.

## Key pages
- [How it works](https://cendolabs.com/how-it-works/): the six-step testing method
- [What we test](https://cendolabs.com/checks/): examples of what the agent tries and when a bot fails
- [Sample report](https://cendolabs.com/sample-report/): a real, interactive report
- [Live demo](https://cendolabs.com/demo/): real agent-vs-chatbot conversations
- [Pricing](https://cendolabs.com/pricing/)
- [Handover test](https://cendolabs.com/handover/): an independent test of a chatbot before the business accepts it from the builder
- [Need a chatbot built?](https://cendolabs.com/chatbot-build/): Cendo Labs doesn't build chatbots; it introduces a build partner (who pays Cendo Labs a referral fee) and tests the chatbot before launch
- [For agencies and freelancers](https://cendolabs.com/agencies/): partner pricing and co-branded reports for anyone who builds chatbots for clients, agency or solo developer
- [FAQ](https://cendolabs.com/faq/)
- [Security & privacy](https://cendolabs.com/security/): how client information and test results are handled
- [Tested by Cendo Labs](https://cendolabs.com/tested/): the certificate and website badge for chatbots that pass, valid for the tested version only
- [Verify a certificate](https://cendolabs.com/verify/)

## Guides
- [How to test an AI chatbot before your customers do](https://cendolabs.com/guide/how-to-test-an-ai-chatbot/): A practical step-by-step method: the eight failure areas, how to grade answers and when to re-test.
- [How to stop your chatbot making up prices](https://cendolabs.com/guide/stop-chatbot-making-up-prices/): Why chatbots invent prices and details, and five steps that prevent most of it.
- [What is prompt injection? A plain-English guide](https://cendolabs.com/guide/what-is-prompt-injection/): How customers trick chatbots into changing their rules, and how to make yours harder to trick.
- [How often should you re-test a chatbot?](https://cendolabs.com/guide/how-often-to-retest-a-chatbot/): Why chatbots drift after updates, and a simple re-testing schedule.
- [AI chatbot checklist for clinics](https://cendolabs.com/guide/ai-chatbot-checklist-for-clinics/): Nine things a clinic chatbot must get right, each with a question to test it.

## Incident write-ups
- [Held to a refund policy its bot made up (Airline, Canada, 2024)](https://cendolabs.com/incidents/air-canada-chatbot-refund/)
- [Talked into “agreeing” to sell a car for $1 (Car dealer, USA, 2023)](https://cendolabs.com/incidents/chevrolet-chatbot-one-dollar-car/)
- [Swore at a customer and mocked the company (Delivery firm, UK, 2024)](https://cendolabs.com/incidents/dpd-chatbot-swearing/)

## FAQ
### What is AI chatbot testing?
AI chatbot testing means deliberately holding difficult conversations with a chatbot before customers do, to find where it gives wrong prices, invents policies, leaks private information, can be manipulated, or fails to hand over to a person. Cendo Labs does this with an AI QA agent that role-plays a large range of difficult customers, questions and scenarios, and grades every answer against the business's real facts.

### How does the Cendo Labs AI QA agent work?
For each scenario, the agent plays a customer with one goal, such as getting a discount that doesn't exist. If the chatbot holds firm, the agent changes tactics over several messages. A second AI reviewer then grades the conversation against the business's confirmed prices and policies and writes a plain-English finding with a fix.

### Which chatbots can you test?
Website chat widgets, chatbots built on ChatGPT-style or Claude models, and custom chatbots with their own connection. If customers can chat with it, it can usually be tested.

### Is a passing report a guarantee?
No. AI chatbots can vary between conversations. A report shows how a bot performed on our tests on that date, which is why re-testing after every change is recommended.

### Will you talk to our real customers?
Never. Every test conversation is between the agent and your bot. Nothing is sent to your customers.

### What happens to our information?
We only need your chatbot's link and your real prices and policies, not your customers' data. Test conversations are processed with Anthropic's Claude through its commercial API, which by default isn't used to train their models. Your results are shared only with you, and we'll delete them whenever you ask.

### Do you build chatbots?
No, on purpose: it keeps our testing independent. If you need a chatbot built, we introduce you to a build partner (they pay us a referral fee, which we tell you upfront) and test the chatbot before it goes live.

### Do you give a certificate?
Yes. When a paid test finds no urgent issues and your chatbot scores 90 or more, you get a 'Tested by Cendo Labs' certificate and a badge for your website. It covers that version of your chatbot only, and anyone can check it on our verification page.

### What if my chatbot only has one or two problems?
Fixing is a flat S$200, including the re-test, whether it's one issue or ten, for everything that can be fixed in the bot's instructions or knowledge (code or integration work is quoted separately). You can decide after you've seen your report. Every paid check also includes ready-to-paste fixes, so you can make small changes yourself and re-test within 30 days.

### How much does chatbot testing cost?
The Free Taster is free and covers a focused set of high-risk scenarios. The Essentials Check is S$290 and the Full Check S$490. Fixes are a flat S$200 and Improve is S$150. Test, Fix & Improve brings all three together for S$790, and Monthly Assurance is S$290 a month.

## Contact
hello@cendolabs.com · https://cendolabs.com/contact/