How to Build a Chatbot that works with your Brand

Are you one of those who think Tinder is more than a dating app? Then go ahead and read this article! Tinder swipe to choose or discard people was a turning point for user interfaces. A game-changer in mobile devices screens. An interaction that broke the rules between users and mobiles. It's a micro-revolution.

Tinder is only an example of the next big changes in user interfaces. Move detection and VR/AR will drive the real revolution in the UI paradigm. But certainly, chatbots are an indicator of this "revolUItion". Chatbots may be the most famous and consolidated UI changes. They created a new relationship between brands and consumers, a new way to deliver customized experiences, and huge optimizations with artificial intelligence (AI).

One of chatbots' main advantages is its ridiculously easy building process. Maybe you can build a chatbot in a 72-hour hackathon. But you can fail to be successful, too. After building different-sized chatbots at Opentrends, we know enough about their conceptualization, definition, prototyping, and development. Are you interested? Follow the steps to build one!

1. Set up a transdisciplinary team

A copywriter with a text-editing tool is insufficient to build a conversation. The writer's role is as important as that of a UX expert, UI support profile, and developer who knows chatbot platforms, from native tools to Facebook Messenger, Slack, or WhatsApp for Business.

2. Know the brand & its audience

Immersion in your client's digital business is essential to define chatbot goals. Sometimes, they will tell you their two main goals: raise engagement and reduce response time. It is your moment to go further: explore, interact, fight and discover

• how your customer talks on social media
• how FAQS are written... etc. Ask wherever you think a chatbot can make users' lives easier. Observe the relationship between the brand and its audience and vice versa.
   

This analysis is crucial to
building a user-centered chatbot
and deliver a solid proposal
to satisfy your KPIs.

3. Build a specific chatbot

When we build a bot, we should decide to make it specific, as opposed to not being an ‘all-rounder’, despite the temptation to get overexcited about potential capabilities. According to reports, 70% of the 100,000+ Facebook Messenger bots fail to fulfill simple user requests. This is partly a result of developers failing to narrow their bot down to one strong area of focus.

Card Sorting exercises are an extraordinary way to define and prioritize what a chatbot will be used for. They are also the first approach for tone and voice adaptation. For example, if we need to build a bot to help users resolve some FAQs, we should know which of the top 10 questions have answers that can be painful for them and which are the harder questions to answer.

4. Adapt to brand voice and tone

Brands are more than a logo and a name. They are a set of experiences with multiple user touchpoints and chatbots are one of them. For that reason, you will want to build a chatbot that is aligned with the brand storytelling structure. Create a customized personality and voice tone for this channel.
 

Pro Tip!

Find brand style guides before writing any words or idiomatic expressions, and co-create with customers to define them. It can be as easy or as difficult as you want.

5. Build a Conversational Tree

Until today, the vast majority of bots are built using decision-tree logic. So, it’s time for a UX Designer and copywriter to align brand, user journeys, and technology specs. Conversational trees must include all touchpoints between the user and the bot and anticipate error messages or user trash-talk reactions. You can also identify and mark user moods in these touchpoints with emoji or basic iconography. That’s very helpful before implementing voice and tone.

We recommend diagrams.net (formerly draw.io) for collaborative conversational trees. This deliverable shouldn’t include final content but a conversational tree is also important to align workflows between UX and writers. We strongly recommend using codes to identify content pieces and find them easily in an Excel collaborative document.

6. Write, and rewrite

Now that you have all the elements on the table, it's time to write and rewrite. It's not only about picking the right words to transmit the brand voice tone; it's about the conversational structure and user feelings at every touchpoint. Focus on enabling language to make chatbot usability easier. In other words, UX Writing time is needed to be coherent and make conversational trees usable.

Don't be influenced by robotic words! You write for people, and " you don't want to be a machine!" So, write content in a conversational way. Think about your WhatsApp or Messaging chats. Use emojis and visual content to help users talk and browse simultaneously in the same user interface.

7. Fast prototyping

Until now, every step happened in an Excel document and app.diagrams.net conversational tree. They are excellent work documents but aren't exciting enough to show your clients. The best practice for understanding a chatbot is showing your customers an actual one. Put them in the user context and prototype quickly. It is essential in bot-building processes. There are many free tools for chatbot fast prototyping. We recommend Bot Society, but it is not 100% reliable. If you prototype with Bot Society, consider character limitations or image use.

8. Choose a reliable platform

Facebook Messenger is the most popular platform to host a chatbot. But it's not the only one. You should choose the one that strategically and technically suits better your customer needs: Slack, WhatsApp, Twitter, Telegram…, or a native chatbot. At Opentrends, we have invested in Hubtype through our Venture Builder, The Carrot Cake. This award-winning chatbot startup is our best ally for building and managing chatbots.

Beyond development, Hubtype allows you to manage the bot efficiently, customize analytics, and, most importantly, take control of conversations with users anytime! The Hubtype team has built an amazing 3-Steps Guide to creating a Facebook Messenger Chatbot. Have a peek at their blog posts!

9. Don't forget VUI

We do not only write for users. We need to get ready to talk to them. At Opentrends, we built a concept with the Google Assistant app to book meeting rooms. Read the full case study here. Consider defining a chatbot as a first step to evolving into a digital voice assistant. If you have worked hard with voice and tone definition, adding expressions will be easier.

10. Test me if you can

It may sound obvious, but we'll repeat once again: Testing will put your chatbot (and any product or service) in the place where it belongs. Before its launching, test it with as many users as you can. No matter if it is a Guerrilla Test or a User Lab. But please, test! It will help you understand the audience and perhaps even destroy your hypothesis. Because without a doubt, User Killed The Technology Star!

Written by MM.