Updated on December 12, 2022

Adding questions and examples is only half the work done. Your virtual assistant needs training to process the questions and answers you’ve added.


At this point, you would have finished adding all your intents and examples.

How is this useful?
Like any human, AI-generated assistant needs time to train and digest the information that you have input into its brain.  If your knowledge base is big, allow the virtual assistant some time to train before you publish the bot.

How does this work?

When you’re training the virtual assistant, it is actually applying its Natural Language Processing (NLP) abilities, to learn and understand the questions and start behaving like an Artificial Intelligence (AI) bot.

Natural Language Processing – the machine’s programmed ability to process and analyse large quantities of natural language data.

Steps to save, train and publish

  1. Click ‘Save’. There will be a pop-up banner to notify users on success.
  2. Click ‘Train’. There will be a pop-up banner to notify users on that the Bot was trained successfully.
  3. Lastly, click ‘Publish’ for your changes to go live on your Bot.
  4. To check if  your questions have been published, click ‘Show Previous Versions’. If the questions have been published, you would see a green Published indicator on the latest version.
Did we help you?

Learn more about KeyReply

To see our Conversational AI in action, sign-up for a guided walk-through and see how our platform can be tailored for your organization’s needs