At this point in the process, you have created your bot, given it some data, and tested it. After you deploy your bot, it will start to gather conversation data. It's important to regularly review these conversations and make improvements to your bot. This is how your bot can continue to get smarter and more helpful over time.
Review and Learn
You can review every conversation and message. Pay attention to what users are really asking for. While you can't cater to every user behavior, you can try to address common points of friction or frustration you notice. There are two main places to review conversation data:
- Insights: The Dashboard, Journeys, and Conversations tabs allow you to view data about your conversations and messages as well as entire conversations in context. You can make adjustments to intents or turn the entire conversation into a story for the bot to use as training data.
- The NLU Inbox: The NLU Inbox allows you to view individual messages from users as they come in. You can use this view to make fast and precise improvements based on trends you notice.
Improve Your Bot
While reviewing, you can take actions to teach your bot how to be even better in future conversations. The following list describes situations that require improvement and what you can do:
- Low intent classification confidence: If the intent classification is correct, add more training data for the intent to make the bot more confident. If the intent classification is not correct, change it.
- Low bot action prediction confidence: Add more training data to make the bot more confident in what action it should take in this situation.
- User frustration: This may include requests for transfer to a human (handover
Any contact message that should trigger transfer to a live agent), repeating what they already said previously, or insults. Add more training data about their issue, or adjust the NLU confidence threshold in fallback. This can tell your bot to use handover sooner if it isn't confident how to help the user. - “Out_of_scope” intent or fallback behavior: This may include a user asking for something your bot is not capable of, or your bot using fallback too early. Check for and fix any misclassified intents to verify that your bot didn't simply misunderstand the situation. Add a new story or rule to show your bot what to do next time.