From Manual to Automated Testing for Conversational AI
Workshop by Christoph Börner
29. 09. from 13:00 to 17:00 CET
About this workshop
Testing is a crucial enabler for the success of chatbots and voice assistants. Doing it manually requires enormous time and effort. As DevOps and AIOps grow in importance, automated testing will remain critical to ensure that bots do what their designers intended. Unlike traditional software where the application follows a predefined flow, a chatbot runs without any restrictions. Talking to a chatbot has no barriers. Combining this with unpredictable user behavior, it becomes of utmost difficulty to verify the correctness of conversational AI. Training data and test sets are infinitely large. In fact, quantity plays a mature role in quality assurance for bots but makes it impossible to test manually. We will tackle the main questions arising: "Why are bots failing", "What and how should you test?" and of course mainly "How can we automate the testing and training". In a hands-on workshop, every attendee will gain experience in automating the first tests for chatbots and learn how to set up a full end-to-end testing pipeline.
Key takeaways
- What and how should you test
- Why are bots failing
- How can we automate the testing and training
Who will benefit?
-
Testers, Developers, Devops
Equipment requirements
-
Botium Box Mini registration