How to fix your Microsoft LUIS NLP Chatbot

Wondering how to fix your Microsoft LUIS chatbot?

Testing and fixing a Microsoft LUIS Chatbot can be very time consuming. Where is it going wrong? Are my chatbot fixes working? Why are my fixes now causing other problems? Is there a way of continually monitoring my chatbot's performance?

Our expert Data Model Analyst, Alison Houston, has put together a very handy tutorial for Microsoft LUIS chatbot builders. This guide takes you right from inputting your training data right through to drilling down into why utterances and intents aren't working - and, of course, how to put them right.

What you’ll learn

• Testing Microsoft LUIS data

• Improving correctness and confidence– the key KPIs

• Intent scoring and upgrading

• Individual intent and utterance analysis

• Validating fixes and checking for regressions

• How to use QBox additional features

• Tracking improvements to your model

If you’re looking for a guide rich in detail and with lots of practical guidance, it’s worth giving this one a watch.

Watch the video here:


We hope you found the video useful. If you have any questions about how you can improve your NLP chatbot, please get in touch. We'd be happy to show you what QBox can do!

Ready to give QBox a try? Get 5 free tests here.

Drop us a line to schedule a demonstration here.

See an overview of what QBox can do here.

Sandra Draganoiu

Sandra is Relationship Director at QBox and supports our valued customers through their NLP chatbot lifecycle journey

Follow me on LinkedIn