> For the complete documentation index, see [llms.txt](https://docs.chatlayer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chatlayer.ai/~/changes/zWOY8fNiBBrqneKkuGvA/tutorials/getting-started.md). # Planning your bot Before you start building your bot on Chatlayer, there are a few strategic steps to consider. From defining the use cases to crafting a bot personality – here's how to get started. ### **Define the bot's goal** Before you can start building your bot, you need to know ***why*** **you are building the bot**. What is the goal here? If you want to automate an existing service, what is the current experience like, and how could a bot help you improve it? > For the sake of our [ChooChoo tutorial](https://docs.chatlayer.ai/tutorials/tutorial-your-first-bot), our goal could be something like: *a bot to automate a train booking service so that customers get a similar experience as if they were speaking to an agent, without overwhelming the customer care service.* Some other examples of business goals: * A service-oriented bot for clients to deal with technical issues of their bikes * A bot to track orders * An FAQ bot that generates leads * ... Make sure to look at your business and marketing goals: if one of your goals is to increase customer satisfaction, you may want to add a bot to your customer support team and let it handle the most common FAQs, so your team has more time to focus on the complex cases. ### Define the bot use cases After figuring out the *why* of your bot, it’s time for the *what*. ***What***** is your bot going to do exactly? How will it help the user?** We cannot stress how important it is to figure this out before you start building your bot, as you cannot build something that isn't defined yet. {% hint style="success" %} Based on our experience and customers, we already have a bunch of [template bots](https://docs.chatlayer.ai/tips-and-best-practices/bot-templates?q=templates) that you can easily download and modify. They target many industries, from E-Bikes, to Commerce and Restaurant, so you will surely get some inspiration there. {% endhint %} Here are some good use case for a bot for booking trains: * Book a ticket * Get train schedules * Luggage storage * ... > In the case of our [ChooChoo tutorial](https://docs.chatlayer.ai/tutorials/tutorial-your-first-bot), a use case could be: *book a train ticket from a certain departure city to a certain destination city*. {% hint style="info" %} Make sure that you **prioritize your use cases.** For instance, if your bot is about customer service, maybe a good first use case would be about the question that your customers ask the more about. {% endhint %} ### Understand your tech Now that you know the *why* and the *what* of your bot, it’s important to understand the *where*: ***where***** will your bot live?** Will the bot be integrated with WhatsApp? Can customers engage with it via SMS, Facebook Messenger or on the company website? **What are the restrictions of each channel?** A bot that talks to your users via SMS won’t be able to use as many characters as a bot that only communicates via web. So make sure you understand your tech and its limitations. {% hint style="success" %} Our platform allows you to easily connect your bot to [multiple channels](https://docs.chatlayer.ai/channels/multi-channel) and all your [back-end databases](https://docs.chatlayer.ai/integrations/custom-back-end-integrations#multi-language). That's how you provide your users with a truly delightful experience. {% endhint %} ### Know your user In order to design an experience that feels personal, you need to make it personal. ***Who***** is this user that will engage with your bot?** {% hint style="info" %} Remember, there is no such thing as a universal user! It’s important to know what users want and how they are feeling during the conversation. {% endhint %} Some relevant questions on identifying your users: * What’s their backstory? * Their challenges? * Their motivations? * How familiar are they with your business and using bots in general? * What are their sociodemographic characteristics? ### Craft your bot personality How can you make sure that your users connect with your bot and that the conversation is engaging and representative of real human interaction? By giving your bot a **clear** **personality**. How is your bot going to speak and behave, taking into account your user group expectations? What’s the bot avatar like? Is it female, male, genderless, an animal? Human or abstract? All of these are questions that should be considered to make your bot as coherent as possible. {% hint style="info" %} If you can, use your company branding as a starting point and build on it. You can read more about how to design your bot’s personality [**here**](https://chatbotslife.com/how-to-design-your-chatbots-personality-free-download-dd9eeccffbb9). {% endhint %} ### Script the happy flow Now that you have a clear picture of who’s communicating (your bot persona and your user ID) and what they’re talking about (your use cases), it’s time to write the **dialogues**. **A ‘happy flow’ is** **a dialogue where everything runs the way it’s supposed to run**. The conversation is natural and smooth, and the user reaches their goal in as little steps as possible. Many conversation designers start with the happy flow because it’s the flow of least resistance. {% hint style="info" %} Don't know where to start to draft your flows? Have two people sit back-to-back and improvise a conversation around a use case, with one person playing the user and the other playing the bot. {% endhint %}

Example of a happy flow for a restaurant bot.

{% hint style="info" %} There are many tools that can be used to sketch your happy flow, the first one being the good old pen and paper. If you would like a tool that allows easy sharing with your team though, nice options are [Miro](https://miro.com/) or [Figjam](https://www.figma.com/fr/figjam/). {% endhint %} ### Script the edge cases While Chatlayer's AI technology is very good, it is not yet capable of understanding every user utterance well enough in order to reply in a correct way. So the next step after writing the happy flows is to write out **the most likely ways a user might go off track** and how you’re going to deal with that. {% hint style="info" %} In designing your edge cases, always make sure to strategically guide the user back to an existing flow so that the conversation keeps on running and feels as natural as possible. {% endhint %} What if a user asks your bot how it’s doing? What if they tell the bot they don’t like it? What if they want another suggestion? What happens if the user wants to book a table for two, but one person is allergic to gluten and the other one doesn’t eat fish?

Happy flow and edge cases imagined for a restaurant bot.

{% hint style="success" %} You can find frequently asked questions as [prebuilt intents ](https://docs.chatlayer.ai/understanding-users/natural-language-processing-nlp#intent-pack)packs in our platform's NLP section. These intents are predefined and come with their own expressions, which means you can use them straight away! {% endhint %} ## Lesson recap You know now that before building your bot, you should have in mind: * Why you want to build it * What it is going to do exactly * On which channels it will live * Who are your users * What should the bot personality be like * What happy flow you'd like to see * What edge cases need to be foreseen Check our next tutorial to learn how to make this plan come to life on Chatlayer 👉🏻 --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.chatlayer.ai/~/changes/zWOY8fNiBBrqneKkuGvA/tutorials/getting-started.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.