Chatbots have the potential to revolutionise the way organisations interact with users. Web Usability can help you plan, build and test chatbots.
We need to look at a range of factors to work out where to start:
- Suitable process – is it reasonably self-contained? It should not have so many possible user questions that a chatbot is not appropriate
- Financial impact – how much revenue will it generate or what costs will it save? Does this justify the investment?
- Likelihood of success – an early failure would make it harder sell chatbots into the organisation
- Technical issues – reviewing your APIs and existing systems to understand if it is technically possible to develop a chatbot
Then, in discussion with the client, we can identify the best business process for which to develop a chatbot.
Insight into the top questions that users have will be gained using a range of research approaches including:
- Depth interviews
- Focus groups
- Analysis into external and internal search terms
- Talking to customer facing staff
- Quantitative customer surveys to identify top tasks
These will allow us to develop a detailed understanding of users’ needs and how they would engage with a chat interface in order to develop a prototype.
All chatbot development involves developing a prototype. These are usually not fully functional but emulate the behaviour of the chatbot. The key reasons for prototyping are:
- User Interaction – prototypes allow us to learn how customers interact with the chat interface and how they phrase their questions. This provides us with valuable insight which can then be used to improve the conversation design.
- Platform testing – do users prefer messaging or voice? Prototyping can be across platforms.
- Organisation buy-in – prototypes provide live interfaces which can be presented to stakeholders across the organisation.
- Feasibility testing – prototypes allow us to iterate and gain customer feedback on a variety of ideas.
We plan the research in consultation with the client so the client gets the right solution.
The number of testers required in any usability testing programme depends on a range of factors e.g. what it is wished to achieve, the budget and time available and the target audiences. However, our experience of undertaking testing shows that typically a relatively small proportion of usability problems account for the bulk of the bad user experience: these problems can be identified with a small number of testers
We undertake our own recruitment. This allows us to recruit more accurately to our client’s specification, provide greater flexibility, and treat testers in a decent and ethical way. We are experienced at recruiting testers from a wide range of backgrounds and occupations, and with a range of experience, including testers with visual, motor or cognitive impairment.
The ‘core’ of lab based usability testing is the day when the client stakeholders observe some testing (usually 3-4 testers) and then take part in the discussion to agree issues and actions. If more than 3-4 testers are involved in the research we will conduct these in advanced of the observed testing day and feed the outcomes into the facilitated discussion.
Testing can be undertaken a variety of locations.
We build conversational interfaces using Google Language Process and Node JS:
- We produce custom models using Google’s natural language understanding software. This is the most advanced software of its kind and powers Google Assistant and Google Home.
- All our code is written in node JS. This is the same platform used by Netflix to stream millions of videos each day. Other companies have recently migrated to node to help handle their web traffic, such as Airbnb, Walmart and LinkedIn.
Combined this allows for accurate understanding of human language and lightning fast speed.
The output of the development process is a chat interface tailored to the needs of your organisation on platforms of your choice. Whether this is handling customer queries via a pop up chatbot on your homepage or upselling products on a voice activated Alexa app, we can help create an application that users will love.