Primary chatbot challenges

One of the primary challenges when building any kind of chatbot is producing or obtaining high-quality, diversified training data. The training data that you use across your model’s intents will determine how readily your model picks up on a real user’s true intent when exposed to queries it’s never seen before. So no matter what chatbot framework you’re using (e.g. Microsoft LUIS, IBM Watson, etc.), having high-quality training data is a must. …

You’ve built your chatbot, you’ve carefully and tirelessly trained and tested it, and you’re finally ready to launch it to go live — hoorah! But after monitoring its performance over a period of time after go-live, you notice that some user questions return incorrect intents (so give the wrong answers), despite the fact there’s training data in your model that should result in the correct intent being returned. You also spot that some user questions return the correct intent with very low confidence — so the answer isn’t presented to the user. This leaves everyone very frustrated.

As a chatbot…

This HTTP API allows you to run QBox tests and get results from them programmatically. All urls are relative to the base URL, which is:

Quick video overview

All endpoints return responses in JSON format and, when applicable, accept a request body in JSON format.


The API uses JWT token authentication. Unless otherwise specified all endpoints require authentication. An initial call must be made to get a token which can be used to authenticate subsequent requests.

To authenticate to the initial JWT token retrieval endpoint use the API username and API password found in the QBox user interface…


The Covid-19-QBox-Chatbot Model is free pre-compiled chatbot model that addresses typical questions about the COVID-19 virus to help you handle high volumes of questions from your customers, partners and staff. You simply add it to your current chatbot training data.

We advise you to check that this new set of Intents, Entities & Utterances do not conflict with your current model. To check this out for free, visit


Available for:

With this supplementary model, your chatbot service will help alleviate pressure on your front line staff by filtering…

QBox user base continues to grow by over 20% MoM

During August, we had 155 users run a total of 432 tests across 120 projects. Combined, they saw impressive improvements across their QBox scores:

Correctness: 480 points

Confidence: 607 points

Clarity: 727 points

Chatbot Provider Market Share
Chatbot Provider Market Share
Chatbot Provider Market Share

We welcomed new customers including:

QBox is a great tool for assessing the quality of your chatbot’s training data, but did you know it can also be used to convert training data from one NLP provider’s format to another?

This easy conversion means you can start with a JSON file containing your intents and entities in the IBM Watson format, and seconds later have a ZIP file containing that same information that can be imported into DialogFlow.

QBox currently supports IBM Watson, Microsoft LUIS, QnA-Maker, DialogFlow, Wit, RASA and Amazon LEX and you can do this for free.

Here’s how to convert your training data

Step 1: Export your training data from…

QBox is a free tool that provides a variety of visualisations and metrics that aim to help novice users improve their training data. Those that come from a data science background may however prefer working with established metrics such as precision, recall and F1 and using a confusion matrix to visualise the intersection between different intents (classes).

But how do you go about generating all of this with your Microsoft LUIS, Google Dialogflow or IBM Watson Assistant training data without having to write tons of custom code?

Thankfully, QBox makes this easy and just a few clicks from test the…

This latest release is packed with new and improved features.

  • Amazon Lex alpha release
  • Facebook WIT and Google Dialogflow test speed improvement
  • Better insight of our simple view
  • Pricing change plus PayPal support
  • Time estimation and notification
  • Monitoring time saved and IBM Watson dev-ops
  • Help page, tip of the day
  • Payment in Euro and US Dollars

Welcome to Amazon LEX

After a successful beta test, we are pleased to confirm that Amazon Lex is now fully supported. Anyone with a Lex model can now analyse its performance and improve their customer experience using QBox.

Time is money

We know the faster you get your trained data test…

The biggest improvement in this release is the introduction of support for Microsoft LUIS in QBox Enterprise (QE). This works in exactly the same way as IBM Watson™ Assistant integration. The performance of both providers is very similar.

Other improvements in this sprint

We’ve also added support for the new IAM (Identity and Access Management) authentication mechanism in IBM Watson Assistant. IBM is migrating to this authentication mechanism on a region-by-region basis (the UK has not been migrated yet), and service instances, which were created prior to the migration, will not have their authentication credentials changed.

API connections to your different NLP providers are now…

Benoit Alvarez

Just launched, to analyse and visualise the performance of NLP data model. CTO of Volume. MD of CogCom

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store