We have recently refreshed our branding across our offerings and changed the names of our pricing plans. If you have signed up before Aug 9, 2021, please click Previous plans to view your applicable plans.
We assure you that this change will not impact your product experience, and no action is required on your part.

You can enable your chatbot to understand the intent of your customers in a conversation. You can set up questions and their variations to map them to an answer or a chatbot flow. The bot can detect the intent of the customer and direct them to the right answer. 



Training your bot with Answers

  • Select the required bot from the bot list and click Answers > Train from the menu. Make sure you’re setting up Answers for the latest version of your bot
  • If this is your first time setting up Answers, click on the Start button


Note: Your bot will learn from the questions and answers that you type in. When your customers have questions that are of similar intent to the answers that you've set up, your bot will be able to understand what your customer is asking about and offer the right Answer, from the set of Answers you've configured.

Having multiple variants of the same question helps your bot learn faster. If your bot doesn't recognize a question, you can map it to an existing question and teach your bot so that it will be able to respond to them in the future.


  • Type in the question in the Search/create new question box. If this is the first time you're setting up Answers, or if there are no matches, you can click New question to add a new question. If there are any matches with existing questions, you can add your new question as a variant of the existing question.
  • On the new question configuration page, you can compose an answer to the question, and set up multiple variations  (also referred to as variants) of the same question.

Train your bot section

  • All the questions that need to be improved will be listed in the Train your bot section. Based on the number of variants available, each question will have a tag. The tags are -
    • unmapped if they haven’t been mapped to an answer or a flow
    • unhelpful if they’re marked as unhelpful by customers, and
    • improve coverage if these intents have lesser than five variants or similar unmapped intents present in the training section
  • To improve the intent detection for any questions here, you can use the pencil icon to go to the Edit Intent screen.
  • The Edit Intent screen is similar to the New Intent screen. You can modify the answer, map it to a flow, and set up more multiple variants.

Questions section

  • All the questions that you've set up for your bot to improve intent detection are listed under Questions. You can use this section to keep track of the statistics: such as how many times they were sent, how helpful or not helpful they were. You can also make use of this section to improve intent detections by editing or deleting your existing questions.

Answer settings

  • Learn from your FAQs: Enable your bot to learn from the FAQs that you've set up. When a customer asks a question, the bot will look for any Answers that match the intent of the customers' questions. If a suitable answer isn't available, the bot will share content from the FAQs that you've set up in Freshchat. Admins can configure the number of articles your bot can recommend to the customer. A maximum of 3 articles will be presented to the customer and will be displayed in order of relevance. If an answer is mapped to a bot flow, then the article suggestion is defaulted to 1 article to enable the flow associated with the answer to be triggered.
  • Small Talk: When Small Talk is enabled, your bot can engage your customers in casual conversation, making it a richer, interactive experience. Small talk is available in all 42 languages supported by Freshchat .

Feedback

  • When enabled, feedback will be triggered after every answer given by the bot. You can also map flows to the Yes and No options. Based on what the customer picks, you can choose to map them to a flow. If there is no mapped flow, a thank you message will be shown.

Fallback

  • Fallback flows will be triggered when the bot is not able to respond to the customer’s question. You can also set up variants to the fallback message. To do so, navigate to Configure > Fallback.
  • Connect the fallback message to any flow, so the customers are redirected to this flow whenever the bot cannot take the conversation further. You can also set it up to make the conversation available for agents to pick up.

Transfer to Answers

  • Once you've finished setting up many questions to enable your bot to recognise the intents for each question, you can start making use of the Answers module to help your customers from the bot flow itself. You can transfer conversations from the bot flow to the Answers module by making use of the Transfer to answers action.