Chatbots are everywhere! If you use them wisely, you can save a lot of resources! Isn't that awesome? If you are wondering how you can set up a chatbot yourself, read my tip here.
1. Have you done your homework?
Setting up a chatbot from scratch is no picnic. First, ask yourself – can your current employees do the job, as well? In the first phase of your startup, a simple live chat module like Tawk might very well suffice.
If you still want to move on, make sure you have enough resources at your disposal. A good chatbot needs a lot of time! Just be aware of that. Define your scope considering your budget – and don’t hesitate to start small and scale up at a later stage.
Of course, you also have to decide what your bot is for, exactly. Is it about after sales support? Then, a Q&A page can often be enough. In which case does the chatbot fill the gap between true human interaction and pure support pages?
It needs some time (pic: unspslash.com)
2. Which system fits your needs?
If you have business people (aka non-coders) who operate your bot, consider a graphic interface where bot content can easily be modified with a drag-and-drop function. When you have someone operating your bot who is familiar with coding, you can go with an advanced technology that is more complex, but gives you more flexibility to customize your workflow.
Here is a selection of bots that don't require programming experience:
- Chatfuel provides features like adding content modules or broadcasting updates to your followers automatically. You can also gather information inside Messenger chats using ‘Typeform’ style inputs, or let users request info and interact with your bot with predefined buttons.
- Botsify lets you create bots using a drag and drop template. It includes easy integration for external plugins, AI and machine learning features, to improve the quality of interactions as well as analytics.
- Flow XO has the highest number of integrations (over 100+). It features the most easy-to-use visual editor with pre-built templates for a quick start. However, it is somewhat limited in terms of AI functionality, and remains quite brittle.
- Beep Boop provides an end-to-end developer experience. It is more geared towards providing the best and easiest way of creating slack bots
- Bottr gives you an option to embed your bot on your website. You can also add data from a WordPress or Wikipedia site for better data coverage
For all those who want to use the full potential of a chat bot and are not deterred by programming effort:
- IBM Watson Assistant is my first choice as a platform and gives you a step-by-step backend building experience within the UI. Natural language processing (NLP) is ahead of its time compared to other platforms.
- Microsoft Bot Framework aka Azure Bot Service. It provides an integrated environment specifically for bot development with connectors to other SDKs. Developers can get started with out-of-the-box templates for scenarios such as basic, form, language understanding, question and answer, and more proactive bots.
- Wit.AI (Facebook Bot Engine) makes it easy for developers to build applications and devices that you can talk or text to, by providing an open natural language platform. Wit.AI learns human language from each interaction, and leverages the community by sharing what is learns across developers and use cases. Really witty stuff!
- API.AI (Google Dialogflow) also provides voice and text-based conversational interfaces powered by AI. It can connect with users on Google Assistant, Amazon Alexa, Facebook Messenger, and many other platforms and devices.
3. What are your goals?
When considering the logic (or "flow") within your chatbot conversation, you need to truly understand the goal of your customer (and your business). This goes back to understanding the use case, and, ultimately, what outcome you want from the conversation. To get there, try analyzing previous interactions with customers, or sketch out hypothetical scenarios to predict what questions might come up, and when.
Reach for your goals. (pic: unsplash.com)
4. Chatbot Content - How does that work?
Your main goal sure is to give the user a great bot experience. One way of doing this is to guide them, by giving choices to click on. For example, a yes/no button pops up, or their choices of services appear when the user types “I need help”.
Make sure your chatbot has some rich content in form of sound, graphics, interactive pop-ups, jokes - anything that makes your bot not only practical, but also fun to use. Many people try out a chatbot, just to play around. So – make it dope. ;-)
Also, let the user rate the bot answers. This way, you form a constant feedback loop, to eliminate emerging costumer pain points. But, stay cool, yeah? Don’t let bad feedback get you down, users often only give ratings when they’re unhappy.
Put the pieces together. (pic: unsplash.com)
5. Testing and training
Keep it running: Constantly checking the effectiveness of your chatbot interactions is crucial. Do the dialogues work? Does the user feel understood? Your bot does not have to pass the Turing test, but should serve its purpose.
Set up a continuous cycle of testing, probing and debugging in your preferably small and agile project team. Also, take on the bot feedback from the users, as mentioned above. The pace of change is very high – so make sure to stay ahead of the curve, with your content as well as technology and user satisfaction.
6. Some last tips
- Define your KPIs
- Analyze what you want to achieve with your chatbot
- Supervise and improve your chatbot conversation flow
- Keep talking face to face to your customers and partners
- Scale up bit by bit