A study from Juniper Research states that chatbots will save businesses more than $8 billion per year by 2022.
So yes, chatbots will save you money. They will increase your revenues. You’re convinced you need one for your company.
But hold on. Before rushing into it blindly. Take a few moments to make sure you’re pointing the right way ahead by answering the following questions:
- What business issue are you trying to solve? Identifying a problem or a business optimization that can be addressed by the bot is the first milestone of your project.
- What use cases do you want your bot to answer? Once you have identified the main goal, you need to design the scope of the project — Defining the precise use cases will help you build the architecture of the bot
- What content do you have? Now, think about the content you already have to train the NLP (language understanding) of your bot and how much you’ll have to build — this will help you estimate your amount of work!
- Do you have qualitative APIs? There are essentials if you want your bot to provide real time informations (such as flight information), connect to other services (such as Musement), or let your bot redirect users to a live agent
- What system integration will you need? Pick the systems you’ll need to integrate — Flightstats for real time flight infos? Zendesk to redirect to agents or create tickets? Musement to book activities? Typeform to add a modal form to your bot? — and make sure the connection are feasible.
- On which channel(s) are your users? A bot can be connected to any website, many messaging apps, or even in your app. Your decision must be based on the use — there’s no need to have a bot on Facebook Messenger if you don’t have any followers.
- Will there be enough users to make your bot relevant? Knowing who will your users be and having an approximate idea of how many will use the bot will confirm or reverse the relevance of your project.
- What language(s) do you want your bot to understand & speak?Usually start with maximum two languages, and pick the ones that are mostly needed by your users. Then improve your bot by implementing new languages.
- What resources and skills do you need? If you have tech skills, you can always build a bot on a platform that is not specialized in your industry and without any support nor care. Otherwise, pick a provider that knows your business challenges and that will guide you from A to Z.
- What KPIs do you want to follow to measure success? Last but not least,a bot is far from immutable. Collecting data and following key analytics will help you improve your bot continuously based on its use. Without KPIs you won’t be able to measure your ROI.
One more thing! You’ll need to pick the most efficient and relevant partner to build your bot. At Mindsay, we don’t just build bots, we maintain and improve them and we ensure a great customer care from the beginning of the project and all along. Check one of them on Thalys (in 4 languages).