It’s funny how Copilot wouldn’t do a self-critique.

Shouldn’t Copilot be able to do this? Well, knowing that it might get caught being self-bias or tooting one’s own horn, it declined the invitation to be an evaluator.

I decided to put Microsoft’s Copilot to the test. By using the 10 usability heuristics for user interface design, I gave a 5-star rating on each heuristic before tabulating an overall 5-star rating.

As Microsoft attempts to differentiate itself from its uprising competitor, ChatGPT, it has aggressively added various features over quick succession, including a free use of GPT-4 (for now). Given its pace, could there be some issues with its overall user experience?

Before we dive in, I invite you to give your own rating too, either through the poll below or in the comments. I would be interested in gathering as many responses as possible and creating a follow-up post on the results.