Skip to main content

Get started with Answer training

What is Answer Training?​

Bots understand chatters' questions by comparing them to a list of sample questions. We call these sample questions the Training Questions. Each Answer has its own unique list of Training Questions.

The bot does more than find exact matches or keywords when comparing Answer Training—it uses an algorithm to analyze the answer training as a whole, looking for patterns. Things like synonyms and phrasing variations are all accounted for.

You bot can do all this in multiple languages, too. If your bot is equipped with the multilingual feature, you can train your bot in any language that you've enable in your multilingual settings.

Answer Training is located at the top of the workspace of the Answers view on the bot dashboard. To learn more about how to train your bot, see Train a bot.

How bots use Training​

When a chatter asks a Question, the bot references its Training before it decides how to answer. The following occurs:

  1. The bot compares the chatter’s Question to its Training Questions.

  2. If the bot is confident that it has a match, it serves that Answer to the chatter.

If the bot is not confident, it will provide a Not Understood or Needs Clarification Answer.

Training best practices​

The Training process requires an initial proactive period, followed by ongoing management. However, as the bot learns how to respond to chatters’ questions, adding new Training Questions isn’t as important as maintaining and reviewing the Training Questions in place.

Make your Training robust​

  • Use synonyms and creative sentence composition to prepare your bot for various chatter questions. Avoid single-word Training, which lack the context to provide meaningful responses to your chatters.

  • As you create Training Questions, consider different perspectives and levels of experience with your product/service.

  • Aim for 15-20 Training Questions for every Answer in your bot.

    When an Answer’s Training is limited, the bot will be less confident about how to respond and will be more likely to respond with Not Understood. Conversely, when an Answer has too much Training associated with it, your bot is more likely to serve it to chatters in inappropriate contexts. 15-20 Training Questions for each Answer is the sweet spot between both scenarios, where your bot is most likely to have the right amount of information to know when to serve the Answer to chatters.

Make your Training specific and unique​

  • Training Questions should be directly related to the Answer content.

  • A question cannot be trained for multiple Answers. If you do attempt to add a duplicate question, you will be provided with messaging identifying where the duplicate exists. None of the questions in the batch will be trained until the duplicate is removed.

  • If multiple Answers have similar Training, there are two solutions:

    • Create a general Menu Answer with Training that accounts for all the specific sub-Answers (move Training from specific Answers to Menu Answer). Direct chatters to specific Answers using Quick Reply buttons in the Menu.

    • Merge the Answers into one and consolidate the Training.

Maintain your Training​

  • Training requires ongoing review and optimization. We recommend that you regularly audit Training Questions for each Answer and remove Training that is irrelevant. For example, remove Training that includes personal situations, scenario-based questions, questions in languages other than the bot’s native language, or phrases that are unrelated to the bot’s content.

  • Periodically audit your bot to ensure you don't have Answers that have too many or too few Training Questions. Watch this video for a demonstration:

Have any questions? Contact your Ada team—or email us at .