> For the complete documentation index, see [llms.txt](https://help.pickyassist.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.pickyassist.com/setting-up-guide/smart-replies/train-module/training-bot-introduction.md). # Training Bot Introduction Learn How to Train Bot Using the train module you can train the virtual agent by adding more questions, dialogue, keywords, phrases and their best answer, you can also upload FAQ from an excel /csv sheet, Setup Smart Actions, Small Talks, Reply with Media Files etc ## Creating an efficient answer bot with Smart Replies Smart Replies can answer 50% of your customer general queries if you have trained it well as per your business requirements. ## Understand Questions Understand your customers questions from previous conversations , you can refer to your email , WhatsApp, SMS and even call centre to analyse the most asked questions by your customers. You have the option to enter Question Variations i.e one question can be asked in many ways. ## Segregate Topics / Categories Segregate the questions into various topics / categories, topics may differ from business to business some of the common topics are as below; Pricing \ Billing \ Payments \ Delivery \ Offers \ Product 1\ Produce 2\ Contact\ About\ Small Talks --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://help.pickyassist.com/setting-up-guide/smart-replies/train-module/training-bot-introduction.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.