How can I access QBox?

To access QBox, just register for a free account today. Or take a look at our pricing plans.

How much does it cost?

Sign up for a free account, which allows you to run 5 tests through QBox. Once you've had the trial, you can upgrade.

Take a look at our pricing plans for further details.

How many users can I add to my account?

QBox supports multiuser collaboration and shared projects, enabling teams to work together effortlessly. To find out which plans support multiple users, see pricing.

Can you access my data?

To analyze your model, QBox accesses and stores only your model's training data (rather than any live data).

To monitor your model (available in these plans), QBox accesses and stores both your model’s training data and live data. This is an option that must be explicitly opted in to but can be opted out of anytime.

If you have any questions or concerns, please don't hesitate to contact us.

Which AI providers do you support?

QBox is technology-agnostic. Here are the NLP providers that we support:

Who's working with QBox?

A number of companies are already using QBox. Those that work with natural-language data models have found the most value because they already encounter the challenges of improving or scaling their existing models. We also help businesses kick-start their journey with conversational data models, with support and advice from leading institutes like Gartner.

How can I get started?

To access QBox, you need to register here. If you have problems getting started, please don't hesitate to contact us. We're happy to provide support.

Do you offer any training?

Of course! If you’d like to arrange a demo, please get in touch.

How does QBox evaluate my chatbot?

QBox builds upon industry standard cross‑validation techniques to provide a multidimensional view of how your training data performs, and which intents need improving. With your training data in QBox, you can choose between two types of test:

QBox test (Default test type) -
QBox uses custom cross‑validation techniques incorporating K‑fold and leave‑one‑out (LOOCV) methodologies. Our experience shows that these standard techniques do not perform well for natural language classifiers because of the small number of samples per intent. We’ve modified them considerably to be better applied in the context of natural language processing.

BYOTD (Bring your own test dataset) -
Also known as “Blind Data” or “Test data” - QBox uses utterances you the tester have labelled with the expected intent.

Once you reach this milestone, you can optionally run some tests with your own test dataset to see how your model responds to a wider range of user interactions.

How do I submit a Subject Access Request?

In line with GDPR, you have the right to submit a Subject Access Request. Just email us with your request.

How do I submit a deletion request?

Please contact us to submit a deletion request.

If you request deletion, your account will be cancelled and all of your cookie data will be deleted. Any data stored by us will either be anonymized and retained for reporting purposes, or deleted.

We only anonymize data where we know we are expecting personal data (if, for example, we asked you for your name). If you believe you have provided personal data where we are not expecting it, please contact us.