Nice app !! This looks promising as people were raising concerns how much the magics or operators of the world can scale relying on humans to answer your queries. I'm interested to know more about tech involved in building this. You said it uses Deep Learning for NLP, but can you elaborate as what type of neural networks you have used like Recursive or Recurrent Neural networks or any other open source technologies that you find useful.
I also liked your approach of scaling gradually by restricting the scope of queries that myra can answer.
Thank you for the feedback. Yes - I think of it as the 80/20 use case - humans are great for the long tail, but there is no good reason not to automate the top 80% of the use cases first.
The tech is evolving. Recurrent NNs, word embeddings. Standard python libraries mostly. Nvidia CUDA backend for speed.
