NLP based test automation : Tools, ideas and other recommendations?

Hi folks.

Apologies for this preamble, but to set the context: At the moment, we have API as well as UI-based auto scripts across desktop and web apps. I’m looking at ways to enhance our approach to test automation. We’re exploring new tools (COTS, open and freeware) including for mobility testing. I am also looking at AI/ML - for which I have some reference for.

The question or request for those who might be able to help is on the use of NLP (natural language processing) for automating tests.

  • Have you implemented it? If so, what was your experience?
  • What tools would you recommend?
  • What other ideas or approach would you recommend?
  • Lastly, if you have worked with a consultancy to implement it, what was the lessons? This is a sticking point for me as I am reliant on 3rd parties and specialist skills are always tricky.

I’m looking forward to anyone’s suggestions or thoughts on this. Thanks in advance.

I’m afraid I don’t have any suggestions, but I do have some questions. What benefit are you hoping that the NLP will provide? What are other approaches not providing?

1 Like

Hi, initial disclaimer: I’ve never used NLP solutions on real-life projects so far.
Similarly to what @bobs raised, what are you trying to achive? Better test automation maintanability? Increase readability? Improve understanding for whoever is going to read the test scenarios? Have business people (or other with low coding skills) be able to write test automation scenarios? Are you trying to adopt BDD ?

I’m aware that Functione supports it; I’ve used Functionize but not NLP itself. Maybe you can try it out and see how it goes.
I will try it myself and if I come to some conclusion, I’ll share it here.

Try out testRigor, you can just write steps in simplified plain English as described here.
We have a forever free version online. Or happy to show a demo.